Research

Open, rigorous, and transparent

We drive rigorous and transparent research with open benchmarks, models, and agent systems that advance the science of financial AI.

Research

Selected papers from the community, spanning open benchmarks, financial language models, and agent systems. Full, up-to-date list on Google Scholar; open benchmarks, datasets, and models on Hugging Face.

All publications on Google Scholar →
Benchmarks & models on Hugging Face →

2026

When Agents Trade: Live Multi-Market Trading Arena for LLM Agents L. Qian, X. Peng, H. Smith, Y. Han, Y. He, H. Li, Y. Cao, Y. Yu, G. Xiong, P. Lu, et al. ACM Web Conference (WWW) 2026 PDF Talk Space Agent-Market-Arena 9 ♡

@inproceedings{DBLP:conf/www/QianPSHHLCYXLWZ26,
          author       = {Lingfei Qian and
                          Xueqing Peng and
                          Hanley Smith and
                          Yi Han and
                          Yueru He and
                          Haohang Li and
                          Yupeng Cao and
                          Yangyang Yu and
                          Guojun Xiong and
                          Peng Lu and
                          Yan Wang and
                          Vincent Jim Zhang and
                          Huan He and
                          Alejandro Lopez{-}Lira and
                          Jimin Huang and
                          Jian{-}Yun Nie and
                          Sophia Ananiadou},
          editor       = {Hakim Hacid and
                          Yoelle Maarek and
                          Francesco Bonchi and
                          Ido Guy and
                          Emine Yilmaz},
          title        = {When Agents Trade: Live Multi-Market Trading Arena for {LLM} Agents},
          booktitle    = {Proceedings of the {ACM} Web Conference 2026, {WWW} 2026, Dubai, United
                          Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled
                          for June 29 - July 3, 2026},
          pages        = {7833--7844},
          publisher    = {{ACM}},
          year         = {2026},
          url          = {https://doi.org/10.1145/3774904.3792821},
          doi          = {10.1145/3774904.3792821},
        }

Herculean: An Agentic Benchmark for Financial Intelligence X. Peng, Z. Xie, Y. Cao, H. Li, L. Qian, Y. Wang, V. J. Zhang, H. He, X. Ai, L. Ma, et al. arXiv preprint (2605.14355) PDF Dataset Herculean 878 ↓

@misc{thefin_herculean,
          title  = {Herculean: An Agentic Benchmark for Financial Intelligence},
          author = {X. Peng and Z. Xie and Y. Cao and H. Li and L. Qian and Y. Wang and V. J. Zhang and H. He and X. Ai and L. Ma and others},
          year   = {2026},
          eprint = {2605.14355},
          archivePrefix = {arXiv}
        }

FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures F. Zhang, M. Song, R. Elbadry, Y. Chen, S. Wang, Y. Zhou, X. Zheng, Y. He, et al. arXiv preprint (2604.05966) PDF

@article{DBLP:journals/corr/abs-2604-05966,
          author       = {Fan Zhang and
                          Mingzi Song and
                          Rania Elbadry and
                          Yankai Chen and
                          Shaobo Wang and
                          Yixi Zhou and
                          Xunwen Zheng and
                          Yueru He and
                          Yuyang Dai and
                          Georgi Georgiev and
                          Ayesha Gull and
                          Muhammad Usman Safder and
                          Fan Wu and
                          Liyuan Meng and
                          Fengxian Ji and
                          Junning Zhao and
                          Xueqing Peng and
                          Jimin Huang and
                          Yu Chen and
                          Xue Liu and
                          Preslav Nakov and
                          Zhuohan Xie},
          title        = {FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction
                          Financial Disclosures},
          journal      = {CoRR},
          volume       = {abs/2604.05966},
          year         = {2026},
          url          = {https://doi.org/10.48550/arXiv.2604.05966},
          doi          = {10.48550/ARXIV.2604.05966},
          eprinttype   = {arXiv},
          eprint       = {2604.05966},
        }

Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments Y. Han, L. Qian, Y. Wang, Y. He, X. Peng, D. Feng, Y. Chen, H. Li, Y. Cao, et al. arXiv preprint (2603.23638) PDF

@article{DBLP:journals/corr/abs-2603-23638,
          author       = {Yi Han and
                          Lingfei Qian and
                          Yan Wang and
                          Yueru He and
                          Xueqing Peng and
                          Dongji Feng and
                          Yankai Chen and
                          Haohang Li and
                          Yupeng Cao and
                          Jimin Huang and
                          Xue Liu and
                          Jian{-}Yun Nie and
                          Sophia Ananiadou},
          title        = {Can {LLM} Agents Be CFOs? {A} Benchmark for Resource Allocation in
                          Dynamic Enterprise Environments},
          journal      = {CoRR},
          volume       = {abs/2603.23638},
          year         = {2026},
          url          = {https://doi.org/10.48550/arXiv.2603.23638},
          doi          = {10.48550/ARXIV.2603.23638},
          eprinttype   = {arXiv},
          eprint       = {2603.23638},
        }

Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation Y. Wang, Y. Han, L. Qian, Y. He, X. Peng, D. Feng, Z. Xie, V. J. Zhang, R. Guo, et al. arXiv preprint (2602.16990) PDF

@article{DBLP:journals/corr/abs-2602-16990,
          author       = {Yan Wang and
                          Yi Han and
                          Lingfei Qian and
                          Yueru He and
                          Xueqing Peng and
                          Dongji Feng and
                          Zhuohan Xie and
                          Vincent Jim Zhang and
                          Rosie Guo and
                          Fengran Mo and
                          Jimin Huang and
                          Yankai Chen and
                          Xue Liu and
                          Jian{-}Yun Nie},
          title        = {Conv-FinRe: {A} Conversational and Longitudinal Benchmark for Utility-Grounded
                          Financial Recommendation},
          journal      = {CoRR},
          volume       = {abs/2602.16990},
          year         = {2026},
          url          = {https://doi.org/10.48550/arXiv.2602.16990},
          doi          = {10.48550/ARXIV.2602.16990},
          eprinttype   = {arXiv},
          eprint       = {2602.16990},
        }

Ebisu: Benchmarking Large Language Models in Japanese Finance X. Peng, R. Xiang, F. Zhang, M. Song, M. Jiang, Y. Wang, L. Qian, T. Hara, et al. arXiv preprint (2602.01479) PDF

@article{DBLP:journals/corr/abs-2602-01479,
          author       = {Xueqing Peng and
                          Ruoyu Xiang and
                          Fan Zhang and
                          Mingzi Song and
                          Mingyang Jiang and
                          Yan Wang and
                          Lingfei Qian and
                          Taiki Hara and
                          Yuqing Guo and
                          Jimin Huang and
                          Junichi Tsujii and
                          Sophia Ananiadou},
          title        = {Ebisu: Benchmarking Large Language Models in Japanese Finance},
          journal      = {CoRR},
          volume       = {abs/2602.01479},
          year         = {2026},
          url          = {https://doi.org/10.48550/arXiv.2602.01479},
          doi          = {10.48550/ARXIV.2602.01479},
          eprinttype   = {arXiv},
          eprint       = {2602.01479},
        }

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection Z. Liu, Y. Cao, Y. Jiang, M. Kabir, P. Giannouris, C. Xu, Z. Xu, T. Zhu, T. Faisal, et al. arXiv preprint (2601.05403) PDF

@article{DBLP:journals/corr/abs-2601-05403,
          author       = {Zhiwei Liu and
                          Yupen Cao and
                          Yuechen Jiang and
                          Mohsinul Kabir and
                          Polydoros Giannouris and
                          Chen Xu and
                          Ziyang Xu and
                          Tianlei Zhu and
                          Tariquzzaman Faisal and
                          Triantafillos Papadopoulos and
                          Yan Wang and
                          Lingfei Qian and
                          Xueqing Peng and
                          Zhuohan Xie and
                          Ye Yuan and
                          Saeed Almheiri and
                          Abdulrazzaq Alnajjar and
                          Mingbin Chen and
                          Harry Stuart and
                          Paul Thompson and
                          Prayag Tiwari and
                          Alejandro Lopez{-}Lira and
                          Xue Liu and
                          Jimin Huang and
                          Sophia Ananiadou},
          title        = {Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias
                          in Multilingual Financial Misinformation Detection},
          journal      = {CoRR},
          volume       = {abs/2601.05403},
          year         = {2026},
          url          = {https://doi.org/10.48550/arXiv.2601.05403},
          doi          = {10.48550/ARXIV.2601.05403},
          eprinttype   = {arXiv},
          eprint       = {2601.05403},
        }

All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection Y. Jiang, Z. Liu, Y. Cao, Y. He, Z. Xu, C. Xu, Z. Deng, P. Tiwari, X. Chen, et al. arXiv preprint (2601.04160) PDF Talk

@article{DBLP:journals/corr/abs-2601-04160,
          author       = {Yuechen Jiang and
                          Zhiwei Liu and
                          Yupeng Cao and
                          Yueru He and
                          Ziyang Xu and
                          Chen Xu and
                          Zhiyang Deng and
                          Prayag Tiwari and
                          Xi Chen and
                          Alejandro Lopez{-}Lira and
                          Jimin Huang and
                          Junichi Tsujii and
                          Sophia Ananiadou},
          title        = {All That Glisters Is Not Gold: {A} Benchmark for Reference-Free Counterfactual
                          Financial Misinformation Detection},
          journal      = {CoRR},
          volume       = {abs/2601.04160},
          year         = {2026},
          url          = {https://doi.org/10.48550/arXiv.2601.04160},
          doi          = {10.48550/ARXIV.2601.04160},
          eprinttype   = {arXiv},
          eprint       = {2601.04160},
        }

The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models Y. Wang, Y. Xu, N. Shen, J. Su, J. Huang, Z. Zhu arXiv preprint (2601.03425) PDF

@article{DBLP:journals/corr/abs-2601-03425,
          author       = {Yan Wang and
                          Yitao Xu and
                          Nanhan Shen and
                          Jinyan Su and
                          Jimin Huang and
                          Zining Zhu},
          title        = {The Illusion of Specialization: Unveiling the Domain-Invariant "Standing
                          Committee" in Mixture-of-Experts Models},
          journal      = {CoRR},
          volume       = {abs/2601.03425},
          year         = {2026},
          url          = {https://doi.org/10.48550/arXiv.2601.03425},
          doi          = {10.48550/ARXIV.2601.03425},
          eprinttype   = {arXiv},
          eprint       = {2601.03425},
        }

The CLEF-2026 FinMMEval Lab: Multilingual and Multimodal Evaluation of Financial AI Systems Z. Xie, R. Elbadry, F. Zhang, G. Georgiev, X. Peng, L. Qian, J. Huang, et al. ECIR 2026 PDF

@inproceedings{DBLP:conf/ecir/XieEZGPQHDJDGWKSN26,
          author       = {Zhuohan Xie and
                          Rania Elbadry and
                          Fan Zhang and
                          Georgi Georgiev and
                          Xueqing Peng and
                          Lingfei Qian and
                          Jimin Huang and
                          Dimitar Dimitrov and
                          Vanshikaa Jani and
                          Yuyang Dai and
                          Jiahui Geng and
                          Yuxia Wang and
                          Ivan Koychev and
                          Veselin Stoyanov and
                          Preslav Nakov},
          editor       = {Ricardo Campos and
                          Adam Jatowt and
                          Yanyan Lan and
                          Mohammad Aliannejadi and
                          Christine Bauer and
                          Sean MacAvaney and
                          Avishek Anand and
                          Zhaochun Ren and
                          Suzan Verberne and
                          Nan Bai and
                          Masoud Mansoury},
          title        = {The {CLEF-2026} FinMMEval Lab: Multilingual and Multimodal Evaluation
                          of Financial {AI} Systems},
          booktitle    = {Advances in Information Retrieval - 48th European Conference on Information
                          Retrieval, {ECIR} 2026, Delft, The Netherlands, March 29 - April 2,
                          2026, Proceedings, Part {IV}},
          series       = {Lecture Notes in Computer Science},
          pages        = {267--276},
          publisher    = {Springer},
          year         = {2026},
          url          = {https://doi.org/10.1007/978-3-032-21321-1\_37},
          doi          = {10.1007/978-3-032-21321-1\_37},
        }

2025

InvestorBench: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent H. Li, Y. Cao, Y. Yu, S. R. Javaji, Z. Deng, Y. He, Y. Jiang, Z. Zhu, et al. ACL 2025 PDF

@inproceedings{DBLP:conf/acl/LiCYJDHJ0SHQPSX25,
          author       = {Haohang Li and
                          Yupeng Cao and
                          Yangyang Yu and
                          Shashidhar Reddy Javaji and
                          Zhiyang Deng and
                          Yueru He and
                          Yuechen Jiang and
                          Zining Zhu and
                          K. P. Subbalakshmi and
                          Jimin Huang and
                          Lingfei Qian and
                          Xueqing Peng and
                          Jordan W. Suchow and
                          Qianqian Xie},
          editor       = {Wanxiang Che and
                          Joyce Nabende and
                          Ekaterina Shutova and
                          Mohammad Taher Pilehvar},
          title        = {{INVESTORBENCH:} {A} Benchmark for Financial Decision-Making Tasks
                          with LLM-based Agent},
          booktitle    = {Proceedings of the 63rd Annual Meeting of the Association for Computational
                          Linguistics (Volume 1: Long Papers), {ACL} 2025, Vienna, Austria,
                          July 27 - August 1, 2025},
          pages        = {2509--2525},
          publisher    = {Association for Computational Linguistics},
          year         = {2025},
          url          = {https://aclanthology.org/2025.acl-long.126/},
        }

Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance X. Peng, T. Papadopoulos, E. Soufleri, P. Giannouris, R. Xiang, Y. Wang, et al. EMNLP 2025 PDF Talk Model plutus-8B-instruct 45 ↓ · 10 ♡ Datasets Plutus Greek tasks (×9) 617 ↓ Space Open-Greek-Financial-LLM-Leaderboard 10 ♡

@inproceedings{DBLP:conf/emnlp/PengPSGXWQHXA25,
          author       = {Xueqing Peng and
                          Triantafillos Papadopoulos and
                          Efstathia Soufleri and
                          Polydoros Giannouris and
                          Ruoyu Xiang and
                          Yan Wang and
                          Lingfei Qian and
                          Jimin Huang and
                          Qianqian Xie and
                          Sophia Ananiadou},
          editor       = {Christos Christodoulopoulos and
                          Tanmoy Chakraborty and
                          Carolyn Rose and
                          Violet Peng},
          title        = {Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance},
          booktitle    = {Proceedings of the 2025 Conference on Empirical Methods in Natural
                          Language Processing, {EMNLP} 2025, Suzhou, China, November 4-9, 2025},
          pages        = {30176--30202},
          publisher    = {Association for Computational Linguistics},
          year         = {2025},
          url          = {https://doi.org/10.18653/v1/2025.emnlp-main.1535},
          doi          = {10.18653/V1/2025.EMNLP-MAIN.1535},
        }

Selective Preference Optimization via Token-Level Reward Function Estimation K. Yang, Z. Liu, Q. Xie, J. Huang, E. Min, S. Ananiadou EMNLP 2025 PDF

@inproceedings{DBLP:conf/emnlp/YangLXHMA25,
          author       = {Kailai Yang and
                          Zhiwei Liu and
                          Qianqian Xie and
                          Jimin Huang and
                          Erxue Min and
                          Sophia Ananiadou},
          editor       = {Christos Christodoulopoulos and
                          Tanmoy Chakraborty and
                          Carolyn Rose and
                          Violet Peng},
          title        = {Selective Preference Optimization via Token-Level Reward Function
                          Estimation},
          booktitle    = {Proceedings of the 2025 Conference on Empirical Methods in Natural
                          Language Processing, {EMNLP} 2025, Suzhou, China, November 4-9, 2025},
          pages        = {7032--7056},
          publisher    = {Association for Computational Linguistics},
          year         = {2025},
          url          = {https://doi.org/10.18653/v1/2025.emnlp-main.359},
          doi          = {10.18653/V1/2025.EMNLP-MAIN.359},
        }

FLAG-Trader: Fusion LLM-Agent with Gradient-Based Reinforcement Learning for Financial Trading G. Xiong, Z. Deng, K. Wang, Y. Cao, H. Li, Y. Yu, X. Peng, M. Lin, K. E. Smith, et al. Findings of the ACL 2025 PDF

@inproceedings{DBLP:conf/acl/XiongDWCLYPLSLH25,
          author       = {Guojun Xiong and
                          Zhiyang Deng and
                          Keyi Wang and
                          Yupeng Cao and
                          Haohang Li and
                          Yangyang Yu and
                          Xueqing Peng and
                          Mingquan Lin and
                          Kaleb E. Smith and
                          Xiao{-}Yang Liu and
                          Jimin Huang and
                          Sophia Ananiadou and
                          Qianqian Xie},
          editor       = {Wanxiang Che and
                          Joyce Nabende and
                          Ekaterina Shutova and
                          Mohammad Taher Pilehvar},
          title        = {{FLAG-TRADER:} Fusion LLM-Agent with Gradient-based Reinforcement
                          Learning for Financial Trading},
          booktitle    = {Findings of the Association for Computational Linguistics, {ACL} 2025,
                          Vienna, Austria, July 27 - August 1, 2025},
          series       = {Findings of {ACL}},
          pages        = {13921--13934},
          publisher    = {Association for Computational Linguistics},
          year         = {2025},
          url          = {https://aclanthology.org/2025.findings-acl.716/},
        }

UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models Y. Yang, Y. Zhang, Y. Hu, Y. Guo, R. Gan, Y. He, M. Lei, X. Zhang, H. Wang, et al. Findings of NAACL 2025 PDF

@inproceedings{DBLP:conf/naacl/YangZHGGHLZWXHYW25,
          author       = {Yuzhe Yang and
                          Yifei Zhang and
                          Yan Hu and
                          Yilin Guo and
                          Ruoli Gan and
                          Yueru He and
                          Mingcong Lei and
                          Xiao Zhang and
                          Haining Wang and
                          Qianqian Xie and
                          Jimin Huang and
                          Honghai Yu and
                          Benyou Wang},
          editor       = {Luis Chiruzzo and
                          Alan Ritter and
                          Lu Wang},
          title        = {{UCFE:} {A} User-Centric Financial Expertise Benchmark for Large Language
                          Models},
          booktitle    = {Findings of the Association for Computational Linguistics: {NAACL}
                          2025, Albuquerque, New Mexico, USA, April 29 - May 4, 2025},
          series       = {Findings of {ACL}},
          pages        = {5429--5448},
          publisher    = {Association for Computational Linguistics},
          year         = {2025},
          url          = {https://doi.org/10.18653/v1/2025.findings-naacl.300},
          doi          = {10.18653/V1/2025.FINDINGS-NAACL.300},
        }

UCL-Bench: A Chinese User-Centric Legal Benchmark for Large Language Models R. Gan, D. Feng, C. Zhang, Z. Lin, H. Jia, H. Wang, Z. Cai, L. Cui, Q. Xie, et al. Findings of NAACL 2025

@inproceedings{DBLP:conf/naacl/GanFZLJWCCXHW25,
          author       = {Ruoli Gan and
                          Duanyu Feng and
                          Chen Zhang and
                          Zhihang Lin and
                          Haochen Jia and
                          Hao Wang and
                          Zhenyang Cai and
                          Lei Cui and
                          Qianqian Xie and
                          Jimin Huang and
                          Benyou Wang},
          editor       = {Luis Chiruzzo and
                          Alan Ritter and
                          Lu Wang},
          title        = {UCL-Bench: {A} Chinese User-Centric Legal Benchmark for Large Language
                          Models},
          booktitle    = {Findings of the Association for Computational Linguistics: {NAACL}
                          2025, Albuquerque, New Mexico, USA, April 29 - May 4, 2025},
          series       = {Findings of {ACL}},
          pages        = {7945--7988},
          publisher    = {Association for Computational Linguistics},
          year         = {2025},
          url          = {https://doi.org/10.18653/v1/2025.findings-naacl.444},
          doi          = {10.18653/V1/2025.FINDINGS-NAACL.444},
        }

LAiW: A Chinese Legal Large Language Models Benchmark Y. Dai, D. Feng, J. Huang, H. Jia, Q. Xie, Y. Zhang, W. Han, W. Tian, H. Wang COLING 2025 PDF

@inproceedings{DBLP:conf/coling/DaiFHJXZHTW25,
          author       = {Yongfu Dai and
                          Duanyu Feng and
                          Jimin Huang and
                          Haochen Jia and
                          Qianqian Xie and
                          Yifang Zhang and
                          Weiguang Han and
                          Wei Tian and
                          Hao Wang},
          editor       = {Owen Rambow and
                          Leo Wanner and
                          Marianna Apidianaki and
                          Hend Al{-}Khalifa and
                          Barbara Di Eugenio and
                          Steven Schockaert},
          title        = {LAiW: {A} Chinese Legal Large Language Models Benchmark},
          booktitle    = {Proceedings of the 31st International Conference on Computational
                          Linguistics, {COLING} 2025, Abu Dhabi, UAE, January 19-24, 2025},
          pages        = {10738--10766},
          publisher    = {Association for Computational Linguistics},
          year         = {2025},
          url          = {https://aclanthology.org/2025.coling-main.716/},
        }

FMDLLaMA: Financial Misinformation Detection Based on Large Language Models Z. Liu, X. Zhang, K. Yang, Q. Xie, J. Huang, S. Ananiadou ACM Web Conference (WWW) 2025 PDF Space FMD2025 5 ♡

@inproceedings{DBLP:conf/www/LiuZYXHA25,
          author       = {Zhiwei Liu and
                          Xin Zhang and
                          Kailai Yang and
                          Qianqian Xie and
                          Jimin Huang and
                          Sophia Ananiadou},
          editor       = {Guodong Long and
                          Michale Blumestein and
                          Yi Chang and
                          Liane Lewin{-}Eytan and
                          Zi Helen Huang and
                          Elad Yom{-}Tov},
          title        = {FMDLlama: Financial Misinformation Detection Based on Large Language
                          Models},
          booktitle    = {Companion Proceedings of the {ACM} on Web Conference 2025, {WWW} 2025,
                          Sydney, NSW, Australia, 28 April 2025 - 2 May 2025},
          pages        = {1153--1157},
          publisher    = {{ACM}},
          year         = {2025},
          url          = {https://doi.org/10.1145/3701716.3715599},
          doi          = {10.1145/3701716.3715599},
        }

FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR Evaluation Y. He, X. Peng, Y. Cao, Y. Wang, L. Qian, H. Li, Y. Han, R. Xiang, M. Lin, et al. arXiv preprint (2511.14998) PDF Talk Dataset FinCriticalED 88 ↓ · 1 ♡

@article{DBLP:journals/corr/abs-2511-14998,
          author       = {Yueru He and
                          Xueqing Peng and
                          Yupeng Cao and
                          Yan Wang and
                          Lingfei Qian and
                          Haohang Li and
                          Yi Han and
                          Ruoyu Xiang and
                          Mingquan Lin and
                          Prayag Tiwari and
                          Jimin Huang and
                          Guojun Xiong and
                          Sophia Ananiadou},
          title        = {FinCriticalED: {A} Visual Benchmark for Financial Fact-Level {OCR}
                          Evaluation},
          journal      = {CoRR},
          volume       = {abs/2511.14998},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2511.14998},
          doi          = {10.48550/ARXIV.2511.14998},
          eprinttype   = {arXiv},
          eprint       = {2511.14998},
        }

FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs Y. Wang, K. Wang, S. Yang, J. Patel, J. Zhao, F. Mo, X. Peng, L. Qian, J. Huang, et al. arXiv preprint (2510.08886) PDF Talk

@article{DBLP:journals/corr/abs-2510-08886,
          author       = {Yan Wang and
                          Keyi Wang and
                          Shanshan Yang and
                          Jaisal Patel and
                          Jeff Zhao and
                          Fengran Mo and
                          Xueqing Peng and
                          Lingfei Qian and
                          Jimin Huang and
                          Guojun Xiong and
                          Xiao{-}Yang Liu and
                          Jian{-}Yun Nie},
          title        = {FinAuditing: {A} Financial Taxonomy-Structured Multi-Document Benchmark
                          for Evaluating LLMs},
          journal      = {CoRR},
          volume       = {abs/2510.08886},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2510.08886},
          doi          = {10.48550/ARXIV.2510.08886},
          eprinttype   = {arXiv},
          eprint       = {2510.08886},
        }

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application X. Peng, L. Qian, Y. Wang, R. Xiang, Y. He, Y. Ren, M. Jiang, V. J. Zhang, et al. arXiv preprint (2506.14028) PDF Datasets MultiFinBen tasks (×4) 589 ↓ Datasets PolyFiQA tasks (×4) 316 ↓

@misc{thefin_multifinben,
          title  = {MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application},
          author = {X. Peng and L. Qian and Y. Wang and R. Xiang and Y. He and Y. Ren and M. Jiang and V. J. Zhang and others},
          year   = {2025},
          eprint = {2506.14028},
          archivePrefix = {arXiv}
        }

RKEFino1: A Regulation Knowledge-Enhanced Large Language Model Y. Wang, Y. He, R. Xiang, J. Zhao arXiv preprint (2506.05700) PDF

@misc{thefin_rkefino1,
          title  = {RKEFino1: A Regulation Knowledge-Enhanced Large Language Model},
          author = {Y. Wang and Y. He and R. Xiang and J. Zhao},
          year   = {2025},
          eprint = {2506.05700},
          archivePrefix = {arXiv}
        }

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning Z. Xie, D. Orel, R. Thareja, D. Sahnan, H. Madmoun, F. Zhang, D. Banerjee, et al. arXiv preprint (2506.02515) PDF

@misc{thefin_finchain,
          title  = {FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning},
          author = {Z. Xie and D. Orel and R. Thareja and D. Sahnan and H. Madmoun and F. Zhang and D. Banerjee and others},
          year   = {2025},
          eprint = {2506.02515},
          archivePrefix = {arXiv}
        }

MMAffBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs Z. Liu, L. Qian, Q. Xie, J. Huang, K. Yang, S. Ananiadou arXiv preprint (2505.24423) PDF

@article{DBLP:journals/corr/abs-2505-24423,
          author       = {Zhiwei Liu and
                          Lingfei Qian and
                          Qianqian Xie and
                          Jimin Huang and
                          Kailai Yang and
                          Sophia Ananiadou},
          title        = {MMAFFBen: {A} Multilingual and Multimodal Affective Analysis Benchmark
                          for Evaluating LLMs and VLMs},
          journal      = {CoRR},
          volume       = {abs/2505.24423},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2505.24423},
          doi          = {10.48550/ARXIV.2505.24423},
          eprinttype   = {arXiv},
          eprint       = {2505.24423},
        }

FinTagging: An LLM-Ready Benchmark for Extracting and Structuring Financial Information Y. Wang, Y. Ren, L. Qian, X. Peng, K. Wang, Y. Han, D. Feng, X.-Y. Liu, J. Huang, et al. arXiv preprint (2505.20650) PDF Talk Datasets FinTagging tasks (×5) 88 ↓

@article{DBLP:journals/corr/abs-2505-20650,
          author       = {Yan Wang and
                          Yang Ren and
                          Lingfei Qian and
                          Xueqing Peng and
                          Keyi Wang and
                          Yi Han and
                          Dongji Feng and
                          Xiao{-}Yang Liu and
                          Jimin Huang and
                          Qianqian Xie},
          title        = {FinTagging: An LLM-ready Benchmark for Extracting and Structuring
                          Financial Information},
          journal      = {CoRR},
          volume       = {abs/2505.20650},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2505.20650},
          doi          = {10.48550/ARXIV.2505.20650},
          eprinttype   = {arXiv},
          eprint       = {2505.20650},
        }

FinAudio: A Benchmark for Audio Large Language Models in Financial Applications Y. Cao, H. Li, Y. Yu, S. R. Javaji, Y. He, J. Huang, Q. Xie, F. Dimino, X. Liu, et al. arXiv preprint (2503.20990) PDF

@article{DBLP:journals/corr/abs-2503-20990,
          author       = {Yupeng Cao and
                          Haohang Li and
                          Yangyang Yu and
                          Shashidhar Reddy Javaji and
                          Yueru He and
                          Jimin Huang and
                          Zining Zhu and
                          Qianqian Xie and
                          Xiao{-}Yang Liu and
                          Koduvayur Subbalakshmi and
                          Meikang Qiu and
                          Sophia Ananiadou and
                          Jian{-}Yun Nie},
          title        = {FinAudio: {A} Benchmark for Audio Large Language Models in Financial
                          Applications},
          journal      = {CoRR},
          volume       = {abs/2503.20990},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2503.20990},
          doi          = {10.48550/ARXIV.2503.20990},
          eprinttype   = {arXiv},
          eprint       = {2503.20990},
        }

OrdRankBen: A Novel Ranking Benchmark for Ordinal Relevance in NLP Y. Wang, L. Qian, X. Peng, J. Huang, D. Feng arXiv preprint (2503.00674) PDF

@article{DBLP:journals/corr/abs-2503-00674,
          author       = {Yan Wang and
                          Lingfei Qian and
                          Xueqing Peng and
                          Jimin Huang and
                          Dongji Feng},
          title        = {OrdRankBen: {A} Novel Ranking Benchmark for Ordinal Relevance in {NLP}},
          journal      = {CoRR},
          volume       = {abs/2503.00674},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2503.00674},
          doi          = {10.48550/ARXIV.2503.00674},
          eprinttype   = {arXiv},
          eprint       = {2503.00674},
        }

Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance L. Qian, W. Zhou, Y. Wang, X. Peng, J. Huang, Q. Xie arXiv preprint (2502.08127) PDF Model Fino1-8B 608 ↓ · 35 ♡ Model Fino1-14B 278 ↓ Model Fin-o1-8B 146 ↓ · 11 ♡ Model Fin-o1-14B 92 ↓ · 6 ♡ Dataset FinCoT 3.7k ↓ · 15 ♡ Dataset Fino1_Reasoning_Path_FinQA 3.6k ↓ · 40 ♡ Space open-finllm-reasoning-leaderboard 8 ♡

@article{DBLP:journals/corr/abs-2502-08127,
          author       = {Lingfei Qian and
                          Weipeng Zhou and
                          Yan Wang and
                          Xueqing Peng and
                          Jimin Huang and
                          Qianqian Xie},
          title        = {Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance},
          journal      = {CoRR},
          volume       = {abs/2502.08127},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2502.08127},
          doi          = {10.48550/ARXIV.2502.08127},
          eprinttype   = {arXiv},
          eprint       = {2502.08127},
        }

Retrieval-Augmented Large Language Models for Financial Time Series Forecasting M. Xiao, Z. Jiang, L. Qian, Z. Chen, Y. He, Y. Xu, Y. Jiang, D. Li, R. L. Weng, et al. arXiv preprint (2502.05878) PDF Talk Model StockLLM 278 ↓ · 4 ♡ Model FinSeer 9 ↓ · 2 ♡

@article{DBLP:journals/corr/abs-2502-05878,
          author       = {Mengxi Xiao and
                          Zihao Jiang and
                          Lingfei Qian and
                          Zhengyu Chen and
                          Yueru He and
                          Yijing Xu and
                          Yuechen Jiang and
                          Dong Li and
                          Ruey{-}Ling Weng and
                          Min Peng and
                          Jimin Huang and
                          Sophia Ananiadou and
                          Qianqian Xie},
          title        = {Enhancing Financial Time-Series Forecasting with Retrieval-Augmented
                          Large Language Models},
          journal      = {CoRR},
          volume       = {abs/2502.05878},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2502.05878},
          doi          = {10.48550/ARXIV.2502.05878},
          eprinttype   = {arXiv},
          eprint       = {2502.05878},
        }

Open FinLLM Leaderboard: Towards Financial AI Readiness S.-C. Lin, F. Tian, K. Wang, X. Zhao, J. Huang, Q. Xie, L. Borella, M. White, et al. arXiv preprint (2501.10963) PDF Space Open-FinLLM-Leaderboard 7 ♡

@article{DBLP:journals/corr/abs-2501-10963,
          author       = {Shengyuan Colin Lin and
                          Felix Tian and
                          Keyi Wang and
                          Xingjian Zhao and
                          Jimin Huang and
                          Qianqian Xie and
                          Luca Borella and
                          Matt White and
                          Christina Dan Wang and
                          Kairong Xiao and
                          Xiao{-}Yang Liu Yanglet and
                          Li Deng},
          title        = {Open FinLLM Leaderboard: Towards Financial {AI} Readiness},
          journal      = {CoRR},
          volume       = {abs/2501.10963},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2501.10963},
          doi          = {10.48550/ARXIV.2501.10963},
          eprinttype   = {arXiv},
          eprint       = {2501.10963},
        }

2024

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making Y. Yu, Z. Yao, H. Li, Z. Deng, Y. Jiang, Y. Cao, Z. Chen, J. W. Suchow, Z. Cui, et al. NeurIPS 2024 PDF Talk

@inproceedings{DBLP:conf/nips/YuYLDJCCSCLXZSX24,
          author       = {Yangyang Yu and
                          Zhiyuan Yao and
                          Haohang Li and
                          Zhiyang Deng and
                          Yuechen Jiang and
                          Yupeng Cao and
                          Zhi Chen and
                          Jordan W. Suchow and
                          Zhenyu Cui and
                          Rong Liu and
                          Zhaozhuo Xu and
                          Denghui Zhang and
                          Koduvayur Subbalakshmi and
                          Guojun Xiong and
                          Yueru He and
                          Jimin Huang and
                          Dong Li and
                          Qianqian Xie},
          editor       = {Amir Globersons and
                          Lester Mackey and
                          Danielle Belgrave and
                          Angela Fan and
                          Ulrich Paquet and
                          Jakub M. Tomczak and
                          Cheng Zhang},
          title        = {FinCon: {A} Synthesized {LLM} Multi-Agent System with Conceptual Verbal
                          Reinforcement for Enhanced Financial Decision Making},
          booktitle    = {Advances in Neural Information Processing Systems 37: Annual Conference
                          on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,
                          BC, Canada, December 10 - 15, 2024},
          year         = {2024},
          url          = {http://papers.nips.cc/paper\_files/paper/2024/hash/f7ae4fe91d96f50abc2211f09b6a7e49-Abstract-Conference.html},
        }

FinBen: A Holistic Financial Benchmark for Large Language Models Q. Xie, W. Han, Z. Chen, R. Xiang, X. Zhang, Y. He, M. Xiao, D. Li, Y. Dai, et al. NeurIPS 2024 PDF Datasets FinBen tasks (×2) 385 ↓ Datasets FLARE benchmark tasks (×64) 4.6k ↓ Space IJCAI-2024-FinLLM-Learderboard 4 ♡

@inproceedings{DBLP:conf/nips/XieHCXZHXLDFXKK24,
          author       = {Qianqian Xie and
                          Weiguang Han and
                          Zhengyu Chen and
                          Ruoyu Xiang and
                          Xiao Zhang and
                          Yueru He and
                          Mengxi Xiao and
                          Dong Li and
                          Yongfu Dai and
                          Duanyu Feng and
                          Yijing Xu and
                          Haoqiang Kang and
                          Ziyan Kuang and
                          Chenhan Yuan and
                          Kailai Yang and
                          Zheheng Luo and
                          Tianlin Zhang and
                          Zhiwei Liu and
                          Guojun Xiong and
                          Zhiyang Deng and
                          Yuechen Jiang and
                          Zhiyuan Yao and
                          Haohang Li and
                          Yangyang Yu and
                          Gang Hu and
                          Jiajia Huang and
                          Xiao{-}Yang Liu and
                          Alejandro Lopez{-}Lira and
                          Benyou Wang and
                          Yanzhao Lai and
                          Hao Wang and
                          Min Peng and
                          Sophia Ananiadou and
                          Jimin Huang},
          editor       = {Amir Globersons and
                          Lester Mackey and
                          Danielle Belgrave and
                          Angela Fan and
                          Ulrich Paquet and
                          Jakub M. Tomczak and
                          Cheng Zhang},
          title        = {FinBen: {A} Holistic Financial Benchmark for Large Language Models},
          booktitle    = {Advances in Neural Information Processing Systems 37: Annual Conference
                          on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,
                          BC, Canada, December 10 - 15, 2024},
          year         = {2024},
          url          = {http://papers.nips.cc/paper\_files/paper/2024/hash/adb1d9fa8be4576d28703b396b82ba1b-Abstract-Datasets\_and\_Benchmarks\_Track.html},
        }

Harmonic: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection Y. Wang, D. Feng, Y. Dai, Z. Chen, J. Huang, S. Ananiadou, Q. Xie, H. Wang NeurIPS 2024 PDF Talk

@inproceedings{DBLP:conf/nips/WangFDCHAXW24,
          author       = {Yuxin Wang and
                          Duanyu Feng and
                          Yongfu Dai and
                          Zhengyu Chen and
                          Jimin Huang and
                          Sophia Ananiadou and
                          Qianqian Xie and
                          Hao Wang},
          editor       = {Amir Globersons and
                          Lester Mackey and
                          Danielle Belgrave and
                          Angela Fan and
                          Ulrich Paquet and
                          Jakub M. Tomczak and
                          Cheng Zhang},
          title        = {{HARMONIC:} Harnessing LLMs for Tabular Data Synthesis and Privacy
                          Protection},
          booktitle    = {Advances in Neural Information Processing Systems 37: Annual Conference
                          on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,
                          BC, Canada, December 10 - 15, 2024},
          year         = {2024},
          url          = {http://papers.nips.cc/paper\_files/paper/2024/hash/b5aebe9a48398525a9da27a1df827d60-Abstract-Datasets\_and\_Benchmarks\_Track.html},
        }

Dólares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and English X. Zhang, R. Xiang, C. Yuan, D. Feng, W. Han, A. Lopez-Lira, X.-Y. Liu, M. Qiu, et al. ACM SIGKDD (KDD) 2024 PDF

@inproceedings{DBLP:conf/kdd/ZhangXYFHLLQA0H24,
          author       = {Xiao Zhang and
                          Ruoyu Xiang and
                          Chenhan Yuan and
                          Duanyu Feng and
                          Weiguang Han and
                          Alejandro Lopez{-}Lira and
                          Xiao{-}Yang Liu and
                          Meikang Qiu and
                          Sophia Ananiadou and
                          Min Peng and
                          Jimin Huang and
                          Qianqian Xie},
          editor       = {Ricardo Baeza{-}Yates and
                          Francesco Bonchi},
          title        = {D{\'{o}}lares or Dollars? Unraveling the Bilingual Prowess of Financial
                          LLMs Between Spanish and English},
          booktitle    = {Proceedings of the 30th {ACM} {SIGKDD} Conference on Knowledge Discovery
                          and Data Mining, {KDD} 2024, Barcelona, Spain, August 25-29, 2024},
          pages        = {6236--6246},
          publisher    = {{ACM}},
          year         = {2024},
          url          = {https://doi.org/10.1145/3637528.3671554},
          doi          = {10.1145/3637528.3671554},
        }

Back to the Future: Towards Explainable Temporal Reasoning with Large Language Models C. Yuan, Q. Xie, J. Huang, S. Ananiadou ACM Web Conference (WWW) 2024 PDF

@inproceedings{DBLP:conf/www/YuanXHA24,
          author       = {Chenhan Yuan and
                          Qianqian Xie and
                          Jimin Huang and
                          Sophia Ananiadou},
          editor       = {Tat{-}Seng Chua and
                          Chong{-}Wah Ngo and
                          Ravi Kumar and
                          Hady W. Lauw and
                          Roy Ka{-}Wei Lee},
          title        = {Back to the Future: Towards Explainable Temporal Reasoning with Large
                          Language Models},
          booktitle    = {Proceedings of the {ACM} on Web Conference 2024, {WWW} 2024, Singapore,
                          May 13-17, 2024},
          pages        = {1963--1974},
          publisher    = {{ACM}},
          year         = {2024},
          url          = {https://doi.org/10.1145/3589334.3645376},
          doi          = {10.1145/3589334.3645376},
        }

AuditWen: An Open-Source Large Language Model for Audit J. Huang, H. Zhu, C. Xu, T. Zhan, Q. Xie, J. Huang CCL 2024 PDF

@inproceedings{DBLP:conf/cncl/HuangZXZXH24,
          author       = {Jiajia Huang and
                          Haoran Zhu and
                          Chao Xu and
                          Tianming Zhan and
                          Qianqian Xie and
                          Jimin Huang},
          editor       = {Maosong Sun and
                          Jiye Liang and
                          Xianpei Han and
                          Zhiyuan Liu and
                          Yulan He and
                          Gaoqi Rao and
                          Yubo Chen and
                          Zhiliang Tian},
          title        = {AuditWen: An Open-Source Large Language Model for Audit},
          booktitle    = {Chinese Computational Linguistics - 23rd China National Conference,
                          {CCL} 2024, Taiyuan, China, July 25-28, 2024, Proceedings},
          series       = {Lecture Notes in Computer Science},
          pages        = {505--521},
          publisher    = {Springer},
          year         = {2024},
          url          = {https://doi.org/10.1007/978-981-97-8367-0\_30},
          doi          = {10.1007/978-981-97-8367-0\_30},
        }

FinNLP-AgentScen-2024 Shared Task: Financial Challenges in Large Language Models Q. Xie, J. Huang, D. Li, Z. Chen, R. Xiang, M. Xiao, Y. Yu, V. Somasundaram, et al. FinNLP Workshop 2024

@inproceedings{thefin_finnlp24,
          title     = {FinNLP-AgentScen-2024 Shared Task: Financial Challenges in Large Language Models},
          author    = {Q. Xie and J. Huang and D. Li and Z. Chen and R. Xiang and M. Xiao and Y. Yu and V. Somasundaram and others},
          booktitle = {FinNLP Workshop 2024},
          year      = {2024}
        }

Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications J. Huang, M. Xiao, D. Li, Z. Jiang, Y. Yang, Y. Zhang, L. Qian, Y. Wang, X. Peng, et al. arXiv preprint (2408.11878) PDF Talk Model FinLLaMA-instruct 0 ↓ · 9 ♡ Model FinLLaMA 0 ↓ · 5 ♡ Model FinLLaVA 14 ↓ · 24 ♡ Space FinLLaVA

@article{DBLP:journals/corr/abs-2408-11878,
          author       = {Qianqian Xie and
                          Dong Li and
                          Mengxi Xiao and
                          Zihao Jiang and
                          Ruoyu Xiang and
                          Xiao Zhang and
                          Zhengyu Chen and
                          Yueru He and
                          Weiguang Han and
                          Yuzhe Yang and
                          Shunian Chen and
                          Yifei Zhang and
                          Lihang Shen and
                          Daniel S. Kim and
                          Zhiwei Liu and
                          Zheheng Luo and
                          Yangyang Yu and
                          Yupeng Cao and
                          Zhiyang Deng and
                          Zhiyuan Yao and
                          Haohang Li and
                          Duanyu Feng and
                          Yongfu Dai and
                          VijayaSai Somasundaram and
                          Peng Lu and
                          Yilun Zhao and
                          Yitao Long and
                          Guojun Xiong and
                          Kaleb E. Smith and
                          Honghai Yu and
                          Yanzhao Lai and
                          Min Peng and
                          Jianyun Nie and
                          Jordan W. Suchow and
                          Xiao{-}Yang Liu and
                          Benyou Wang and
                          Alejandro Lopez{-}Lira and
                          Jimin Huang and
                          Sophia Ananiadou},
          title        = {Open-FinLLMs: Open Multimodal Large Language Models for Financial
                          Applications},
          journal      = {CoRR},
          volume       = {abs/2408.11878},
          year         = {2024},
          url          = {https://doi.org/10.48550/arXiv.2408.11878},
          doi          = {10.48550/ARXIV.2408.11878},
          eprinttype   = {arXiv},
          eprint       = {2408.11878},
        }

A Report on Financial Regulations Challenge at COLING 2025 K. Wang, J. Patel, C. Shen, D. Kim, A. Zhu, A. Lin, L. Borella, C. Osborne, et al. arXiv preprint (2412.11159) PDF

@misc{thefin_regchallenge,
          title  = {A Report on Financial Regulations Challenge at COLING 2025},
          author = {K. Wang and J. Patel and C. Shen and D. Kim and A. Zhu and A. Lin and L. Borella and C. Osborne and others},
          year   = {2024},
          eprint = {2412.11159},
          archivePrefix = {arXiv}
        }

MetaAligner: Conditional Weak-to-Strong Correction for Generalizable Multi-Objective Alignment of Language Models K. Yang, Z. Liu, Q. Xie, T. Zhang, N. Song, J. Huang, Z. Kuang, S. Ananiadou arXiv preprint (2403.17141) PDF

@article{DBLP:journals/corr/abs-2403-17141,
          author       = {Kailai Yang and
                          Zhiwei Liu and
                          Qianqian Xie and
                          Tianlin Zhang and
                          Nirui Song and
                          Jimin Huang and
                          Ziyan Kuang and
                          Sophia Ananiadou},
          title        = {MetaAligner: Conditional Weak-to-Strong Correction for Generalizable
                          Multi-Objective Alignment of Language Models},
          journal      = {CoRR},
          volume       = {abs/2403.17141},
          year         = {2024},
          url          = {https://doi.org/10.48550/arXiv.2403.17141},
          doi          = {10.48550/ARXIV.2403.17141},
          eprinttype   = {arXiv},
          eprint       = {2403.17141},
        }

No Language Is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks G. Hu, K. Qin, C. Yuan, M. Peng, A. Lopez-Lira, B. Wang, S. Ananiadou, et al. arXiv preprint (2403.06249) PDF

@article{DBLP:journals/corr/abs-2403-06249,
          author       = {Gang Hu and
                          Ke Qin and
                          Chenhan Yuan and
                          Min Peng and
                          Alejandro Lopez{-}Lira and
                          Benyou Wang and
                          Sophia Ananiadou and
                          Wanlong Yu and
                          Jimin Huang and
                          Qianqian Xie},
          title        = {No Language is an Island: Unifying Chinese and English in Financial
                          Large Language Models, Instruction Data, and Benchmarks},
          journal      = {CoRR},
          volume       = {abs/2403.06249},
          year         = {2024},
          url          = {https://doi.org/10.48550/arXiv.2403.06249},
          doi          = {10.48550/ARXIV.2403.06249},
          eprinttype   = {arXiv},
          eprint       = {2403.06249},
        }

2023

PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance Q. Xie, W. Han, X. Zhang, Y. Lai, M. Peng, A. Lopez-Lira, J. Huang NeurIPS 2023 PDF Model finma-7b-full 40 ↓ · 17 ♡ Model finma-7b-nlp 1.1k ↓ · 7 ♡ Datasets FLARE benchmark tasks (×64) 4.6k ↓

@inproceedings{DBLP:conf/nips/XieHZLPLH23,
          author       = {Qianqian Xie and
                          Weiguang Han and
                          Xiao Zhang and
                          Yanzhao Lai and
                          Min Peng and
                          Alejandro Lopez{-}Lira and
                          Jimin Huang},
          editor       = {Alice Oh and
                          Tristan Naumann and
                          Amir Globerson and
                          Kate Saenko and
                          Moritz Hardt and
                          Sergey Levine},
          title        = {{PIXIU:} {A} Comprehensive Benchmark, Instruction Dataset and Large
                          Language Model for Finance},
          booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference
                          on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
                          LA, USA, December 10 - 16, 2023},
          year         = {2023},
          url          = {http://papers.nips.cc/paper\_files/paper/2023/hash/6a386d703b50f1cf1f61ab02a15967bb-Abstract-Datasets\_and\_Benchmarks.html},
        }

Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning W. Han, B. Zhang, Q. Xie, M. Peng, Y. Lai, J. Huang ACM SIGKDD (KDD) 2023 PDF

@inproceedings{DBLP:conf/kdd/HanZXPLH23,
          author       = {Weiguang Han and
                          Boyi Zhang and
                          Qianqian Xie and
                          Min Peng and
                          Yanzhao Lai and
                          Jimin Huang},
          editor       = {Ambuj K. Singh and
                          Yizhou Sun and
                          Leman Akoglu and
                          Dimitrios Gunopulos and
                          Xifeng Yan and
                          Ravi Kumar and
                          Fatma Ozcan and
                          Jieping Ye},
          title        = {Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement
                          Learning},
          booktitle    = {Proceedings of the 29th {ACM} {SIGKDD} Conference on Knowledge Discovery
                          and Data Mining, {KDD} 2023, Long Beach, CA, USA, August 6-10, 2023},
          pages        = {4123--4134},
          publisher    = {{ACM}},
          year         = {2023},
          url          = {https://doi.org/10.1145/3580305.3599951},
          doi          = {10.1145/3580305.3599951},
        }

Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models D. Feng, Y. Dai, J. Huang, Y. Zhang, Q. Xie, W. Han, Z. Chen, A. Lopez-Lira, et al. arXiv preprint (2310.00566) PDF Dataset lendingclub-benchmark 51 ↓ · 1 ♡

@article{DBLP:journals/corr/abs-2310-00566,
          author       = {Duanyu Feng and
                          Yongfu Dai and
                          Jimin Huang and
                          Yifang Zhang and
                          Qianqian Xie and
                          Weiguang Han and
                          Alejandro Lopez{-}Lira and
                          Hao Wang},
          title        = {Empowering Many, Biasing a Few: Generalist Credit Scoring through
                          Large Language Models},
          journal      = {CoRR},
          volume       = {abs/2310.00566},
          year         = {2023},
          url          = {https://doi.org/10.48550/arXiv.2310.00566},
          doi          = {10.48550/ARXIV.2310.00566},
          eprinttype   = {arXiv},
          eprint       = {2310.00566},
        }

The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT over Multimodal Stock Movement Prediction Challenges Q. Xie, W. Han, Y. Lai, M. Peng, J. Huang arXiv preprint (2304.05351) PDF

@article{DBLP:journals/corr/abs-2304-05351,
          author       = {Qianqian Xie and
                          Weiguang Han and
                          Yanzhao Lai and
                          Min Peng and
                          Jimin Huang},
          title        = {The Wall Street Neophyte: {A} Zero-Shot Analysis of ChatGPT Over MultiModal
                          Stock Movement Prediction Challenges},
          journal      = {CoRR},
          volume       = {abs/2304.05351},
          year         = {2023},
          url          = {https://doi.org/10.48550/arXiv.2304.05351},
          doi          = {10.48550/ARXIV.2304.05351},
          eprinttype   = {arXiv},
          eprint       = {2304.05351},
        }