---
title: "FinMRAGBench — paper by Yang et al. (2026)"
description: "The authors also propose FinMRAGAgent, a ReAct-style agent fine-tuned on agentic trajectories that calls search and… 42 references."
authors: ["Shouqing Yang", "Qi Zhang", "Yuhang Yang", "Ruikang Xu", "Yuwei Hou", "Zhulin Jia", "Lirong Gao", "Haobo Wang", "Jinglei Chen", "Jiexiang Wang", "Sheng Guo", "Bo Zheng", "Gang Chen"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.187/"
doi: "10.18653/v1/2026.findings-acl.187"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yang-2026-finmragbench-realistic-complex-benchmark-multi/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-finmragbench-realistic-complex-benchmark-multi/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/33/) / FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis

# FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis

**Authors:** Shouqing Yang, [Qi Zhang](https://md.research.elamur.ai/free/en/authors/qi-zhang/), [Yuhang Yang](https://md.research.elamur.ai/free/en/authors/yuhang-yang/), Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, [Haobo Wang](https://md.research.elamur.ai/free/en/authors/haobo-wang/), Jinglei Chen, Jiexiang Wang, [Sheng Guo](https://md.research.elamur.ai/free/en/authors/sheng-guo/), [Bo Zheng](https://md.research.elamur.ai/free/en/authors/bo-zheng/) and [Gang Chen](https://md.research.elamur.ai/free/en/authors/gang-chen/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.187/) · [PDF](https://aclanthology.org/2026.findings-acl.187.pdf) · [DOI 10.18653/v1/2026.findings-acl.187](https://doi.org/10.18653/v1/2026.findings-acl.187) · [OpenAlex](https://openalex.org/W7166873363)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Financial analysts often need evidence that is spread across several filings, non-adjacent pages, and different formats such as prose, tables, and charts. Earlier financial RAG benchmarks miss this. Some handle only text, some supply the gold context and so skip retrieval, and some draw mostly on a single page. FinMRAGBench addresses these gaps. It is built from a corpus of 723 SEC EDGAR filings (10-K, 10-Q, 8-K) totalling 96,549 pages. Financial experts first selected evidence according to standard analysis practices, such as tracking one firm over time or comparing industry peers, and then wrote 887 verified QA pairs around that evidence. The questions cover five task families. Tests of three multimodal retrievers and 15 generators show that current systems handle both retrieval and reasoning poorly. The authors also propose FinMRAGAgent, a ReAct-style agent fine-tuned on agentic trajectories that calls search and computation tools, and it achieves the best overall scores. The resource offers a realistic way to stress-test multimodal RAG in a domain where mistakes are costly.

## Key points
- **Task families:** The five families are Numerical Reasoning, Explainable Fact Verification, Chart Generation (where the output is executable code), Table Generation, and Knowledge-Intensive Reasoning.
- **Evidence spread:** 88.73% of questions need evidence from several non-adjacent pages, and 75.20% need evidence from more than one document. Solving a question takes about 7.49 agent steps on average.
- **Baseline results:** Average Recall@10 is only 42.46%, and the strongest generator averages 47.13%. FinMRAGAgent, built on Qwen3-VL-8B-Instruct, reaches 59.75%.
- **Chart Generation example:** FinMRAGAgent scores 64.29%, compared with 29.67% for Vanilla RAG, 46.15% for IRCOT, and 31.76% for ViDoRAG. Supervised fine-tuning beats untuned tool use on every task.
- **Retrieval ablation:** Coarse-to-fine retrieval, using hierarchical retrieval filtered by industry, company, and year metadata plus page selection, raises Recall@10 substantially. For Numerical Reasoning it climbs from 36.42 to 75.16.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Peking University](https://md.research.elamur.ai/free/en/universities/peking-university/) — University, Beijing, China · 315 works · 43,268 citations
- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 224 works · 13,587 citations
- [Ant Group](https://md.research.elamur.ai/free/en/companies/ant-group/) — Company, Hangzhou, China · 51 works · 1,211 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (2): [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,341 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works

## Cite

Cite as: Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng and Gang Chen. 2026. FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yang2026finmragbench,
  title = {{FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis}},
  author = {Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng and Gang Chen},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.187},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.187}
}
```

- [← previous FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models](https://md.research.elamur.ai/free/en/papers/weng-2026-finesteer-unified-framework-fine-grained/)
- [next → First Steps in ASR for Cypriot Greek: Challenges and Insights](https://md.research.elamur.ai/free/en/papers/stamou-2026-first-steps-asr-cypriot-greek/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/33/)

## References

42 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mohammad Mahdi Abootorabi, Amirhosein Zobeiri, Mahdi Dehghani, Mohammadali Mohammadkhani, Bardia Mohammadi, Omid Ghahroodi, Mahdieh Soleymani Baghshah, and Ehsaneddin Asgari. 2025. Ask in any modality: A comprehensive survey on multimodal retrieval-augmented generation. arXiv preprint arXiv:2502.088… [find](https://scholar.google.com/scholar?q=Mohammad+Mahdi+Abootorabi%2C+Amirhosein+Zobeiri%2C+Mahdi+Dehghani%2C+Mohammadali+Mohammadkhani%2C+Bardia+Mohammadi%2C+Omid+Ghahroodi%2C+Mahdieh+Soleymani+Baghshah%2C+and+Ehsaneddin+Asgari%2E+2025%2E+Ask+in+any+modality)
2. Anthropic. 2024. Claude 3.5 sonnet. [https://www.anthropic.com/news/claude-3-5-sonnet](https://www.anthropic.com/news/claude-3-5-sonnet). Accessed: 2025-12-23. [↗](https://www.anthropic.com/news/claude-3-5-sonnet)
3. Anthropic. 2025. Introducing claude sonnet 4.5. [https://www.anthropic.com/news/](https://www.anthropic.com/news/) claude-sonnet-4-5. Accessed: 2025-12-23. [↗](https://www.anthropic.com/news/)
4. Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo, Qidong Huang, Jie Huang, Fei Huang, Binyuan Hui, Shutong Jiang, Zhaohai Li, Mingsheng Li, and 45 others. 2025a. [Qwen3-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen3-vl-technical-report/). Preprint, a…
5. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025b. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — [Qwen2.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
6. Chanyeol Choi, Jihoon Kwon, Jaeseon Ha, Hojun Choi, Chaewoon Kim, Yongjae Lee, Jy-yong Sohn, and Alejandro Lopez-Lira. 2025a. Finder: Financial dataset for question answering and evaluating retrieval-augmented generation. In Proceedings of the 6th ACM International Conference on AI in Finance, pages… [find](https://scholar.google.com/scholar?q=Chanyeol+Choi%2C+Jihoon+Kwon%2C+Jaeseon+Ha%2C+Hojun+Choi%2C+Chaewoon+Kim%2C+Yongjae+Lee%2C+Jy%2Dyong+Sohn%2C+and+Alejandro+Lopez%2DLira%2E+2025a%2E+Finder%3A+Financial+dataset+for+question+answering+and+evaluating+retrieval%2D)
7. Michael Krumdick, Rik Koncel-Kedziorski, Viet Dac Lai, Varshini Reddy, Charles Lovering, and Chris Tanner. 2024. Bizbench: A quantitative reasoning benchmark for business and finance. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… [find](https://scholar.google.com/scholar?q=Michael+Krumdick%2C+Rik+Koncel%2DKedziorski%2C+Viet+Dac+Lai%2C+Varshini+Reddy%2C+Charles+Lovering%2C+and+Chris+Tanner%2E+2024%2E+Bizbench%3A+A+quantitative+reasoning+benchmark+for+business+and+finance%2E+In+Proceedings+o)
8. Chanyeol Choi, Jihoon Kwon, Alejandro Lopez-Lira, Chaewoon Kim, Minjae Kim, Juneha Hwang, Jaeseon Ha, Hojun Choi, Suyeol Yun, Yongjin Kim, and 1 others. 2025b. Finagentbench: A benchmark dataset for agentic retrieval in financial question answering. In Proceedings of the 6th ACM International Confer… [find](https://scholar.google.com/scholar?q=Chanyeol+Choi%2C+Jihoon+Kwon%2C+Alejandro+Lopez%2DLira%2C+Chaewoon+Kim%2C+Minjae+Kim%2C+Juneha+Hwang%2C+Jaeseon+Ha%2C+Hojun+Choi%2C+Suyeol+Yun%2C+Yongjin+Kim%2C+and+1+others%2E+2025b%2E+Finagentbench%3A+A+benchmark+dataset+for+a)
9. Harold W. Kuhn. 2010. The hungarian method for the assignment problem. In Michael Jünger, Thomas M. Liebling, Denis Naddef, George L. Nemhauser, William R. Pulleyblank, Gerhard Reinelt, Giovanni Rinaldi, and Laurence A. Wolsey, editors, 50 Years of Integer Programming 1958-2008 - From the Early Year… [find](https://scholar.google.com/scholar?q=Harold+W%2E+Kuhn%2E+2010%2E+The+hungarian+method+for+the+assignment+problem%2E+In+Michael+J%C3%BCnger%2C+Thomas+M%2E+Liebling%2C+Denis+Naddef%2C+George+L%2E+Nemhauser%2C+William+R%2E+Pulleyblank%2C+Gerhard+Reinelt%2C+Giovanni+Rinal)
10. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). arX…
11. Viet Lai, Michael Krumdick, Charles Lovering, Varshini Reddy, Craig Schmidt, and Chris Tanner. 2025. Sec-qa: A systematic evaluation corpus for financial qa. In Proceedings of The 10th Workshop on Financial Technology and Natural Language Processing, pages 221–236. [find](https://scholar.google.com/scholar?q=Viet+Lai%2C+Michael+Krumdick%2C+Charles+Lovering%2C+Varshini+Reddy%2C+Craig+Schmidt%2C+and+Chris+Tanner%2E+2025%2E+Sec%2Dqa%3A+A+systematic+evaluation+corpus+for+financial+qa%2E+In+Proceedings+of+The+10th+Workshop+on+Fin)
12. Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Céline Hudelot, and Pierre Colombo. 2025. [Colpali: Efficient document retrieval with vision language models](https://md.research.elamur.ai/free/en/papers/faysse-2024-colpali-efficient-document-retrieval-vision/). In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenRevie…
13. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
14. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Qianyu Guo, Meng Wang, and Haofen Wang. 2023. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). CoRR, abs/2312.10997.
15. Amin Haeri, Jonathan Vitrano, and Mahdi Ghelichi. 2025. Generative ai enhanced financial risk management information retrieval. arXiv preprint arXiv:2504.06293. — [arXiv:2504.06293](https://arxiv.org/abs/2504.06293) [find](https://scholar.google.com/scholar?q=Amin+Haeri%2C+Jonathan+Vitrano%2C+and+Mahdi+Ghelichi%2E+2025%2E+Generative+ai+enhanced+financial+risk+management+information+retrieval%2E+arXiv+preprint+arXiv%3A2504%2E06293%2E+%E2%80%94+%5BarXiv%3A2504%2E06293%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
16. Shijie Han, Haoqiang Kang, Bo Jin, Xiao-Yang Liu, and Steve Y. Yang. 2024. XBRL agent: Leveraging large language models for financial report analysis. In Proceedings of the 5th ACM International Conference on AI in Finance, ICAIF 2024, Brooklyn, NY, USA, November 14-17, 2024, pages 856–864. ACM. [find](https://scholar.google.com/scholar?q=Shijie+Han%2C+Haoqiang+Kang%2C+Bo+Jin%2C+Xiao%2DYang+Liu%2C+and+Steve+Y%2E+Yang%2E+2024%2E+XBRL+agent%3A+Leveraging+large+language+models+for+financial+report+analysis%2E+In+Proceedings+of+the+5th+ACM+International+Confe)
17. Paul Hopkin. 2018. Fundamentals of risk management: understanding, evaluating and implementing effective risk management. Kogan Page Publishers. [find](https://scholar.google.com/scholar?q=Paul+Hopkin%2E+2018%2E+Fundamentals+of+risk+management%3A+understanding%2C+evaluating+and+implementing+effective+risk+management%2E+Kogan+Page+Publishers%2E)
18. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and 1 others. 2025. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Transactions on Information Systems,…
19. Pranab Islam, Anand Kannappan, Douwe Kiela, Rebecca Qian, Nino Scherrer, and Bertie Vidgen. 2023. Financebench: A new benchmark for financial question answering. CoRR, abs/2311.11944. — [arXiv:2311.11944](https://arxiv.org/abs/2311.11944) [find](https://scholar.google.com/scholar?q=Pranab+Islam%2C+Anand+Kannappan%2C+Douwe+Kiela%2C+Rebecca+Qian%2C+Nino+Scherrer%2C+and+Bertie+Vidgen%2E+2023%2E+Financebench%3A+A+new+benchmark+for+financial+question+answering%2E+CoRR%2C+abs%2F2311%2E11944%2E+%E2%80%94+%5BarXiv%3A2311%2E11)
20. Fangyu Liu, Julian Martin Eisenschlos, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Wenhu Chen, Nigel Collier, and Yasemin Altun. 2023a. [Deplot: One-shot visual language reasoning by plot-to-table translation](https://md.research.elamur.ai/free/en/papers/liu-2023-deplot-one-shot-visual-language/). In Findings of the Association for Computational Linguistic…
21. Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. 2023b. [G-eval: NLG evaluation using gpt-4 with better human alignment](https://md.research.elamur.ai/free/en/papers/liu-2023-g-eval-nlg-evaluation-gpt/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 2511–2522.…
22. Lefteris Loukas, Fabian Billert, Manos Fergadiotis, Prodromos Malakasiotis, and Ion Androutsopoulos. 2025. Edgar-crawler: From raw web documents to structured financial nlp datasets. In Companion Proceedings of the ACM on Web Conference 2025, pages 761–764. [find](https://scholar.google.com/scholar?q=Lefteris+Loukas%2C+Fabian+Billert%2C+Manos+Fergadiotis%2C+Prodromos+Malakasiotis%2C+and+Ion+Androutsopoulos%2E+2025%2E+Edgar%2Dcrawler%3A+From+raw+web+documents+to+structured+financial+nlp+datasets%2E+In+Companion+Proc)
23. Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, and 1 others. 2025. [Finmme: Benchmark dataset for financial multi-modal reasoning evaluation](https://md.research.elamur.ai/free/en/papers/luo-2025-finmme-benchmark-dataset-financial-multi/). arXiv preprint arXiv:2505.24714.
24. Lang Mei, Siyu Mo, Zhihan Yang, and Chong Chen. 2025. A survey of multimodal retrieval-augmented generation. arXiv preprint arXiv:2504.08748. — [arXiv:2504.08748](https://arxiv.org/abs/2504.08748) [find](https://scholar.google.com/scholar?q=Lang+Mei%2C+Siyu+Mo%2C+Zhihan+Yang%2C+and+Chong+Chen%2E+2025%2E+A+survey+of+multimodal+retrieval%2Daugmented+generation%2E+arXiv+preprint+arXiv%3A2504%2E08748%2E+%E2%80%94+%5BarXiv%3A2504%2E08748%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2504%2E08748%29)
25. OpenAI. 2023. [GPT-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). abs/2303.08774.
26. CoRR, OpenAI. 2025. Gpt-5.1: A smarter, more conversational chatgpt. [https://openai.com/index/gpt-5-1/](https://openai.com/index/gpt-5-1/). Accessed: 2025-12-23. [↗](https://openai.com/index/gpt-5-1/)
27. Dong Shu, Haoyang Yuan, Yuchen Wang, Yanguang Liu, Huopu Zhang, Haiyan Zhao, and Mengnan Du. 2025. [Finchart-bench: Benchmarking financial chart comprehension in vision-language models](https://md.research.elamur.ai/free/en/papers/shu-2026-finchart-bench-benchmarking-financial-chart/). arXiv preprint arXiv:2507.14823.
28. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023. [Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions](https://md.research.elamur.ai/free/en/papers/trivedi-2022-interleaving-retrieval-chain-thought-reasoning/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), A…
29. Qiuchen Wang, Ruixue Ding, Zehui Chen, Weiqi Wu, Shihang Wang, Pengjun Xie, and Feng Zhao. 2025a. [Vidorag: Visual document retrieval-augmented generation via dynamic iterative reasoning agents](https://md.research.elamur.ai/free/en/papers/wang-2025-vidorag-visual-document-retrieval-augmented/). arXiv preprint arXiv:2502.18017.
30. Qiuchen Wang, Ruixue Ding, Yu Zeng, Zehui Chen, Lin Chen, Shihang Wang, Pengjun Xie, Fei Huang, and Feng Zhao. 2025b. [VRAG-RL: empower vision-perception-based RAG for visually rich information understanding via iterative reasoning with reinforcement learning](https://md.research.elamur.ai/free/en/papers/wang-2025-vrag-rl-empower-vision-perception/). CoRR, abs/2505.22019.
31. Shuting Wang, Jiejun Tan, Zhicheng Dou, and Ji-Rong Wen. 2025c. [Omnieval: An omnidirectional and automatic rag evaluation benchmark in financial domain](https://md.research.elamur.ai/free/en/papers/wang-2025-omnieval-omnidirectional-automatic-rag-evaluation/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 5737–5762.
32. Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, Long Cui, Xingguang Wei, Zhaoyang Liu, Linglin Jing, Shenglong Ye, Jie Shao, and 1 others. 2025d. [Internvl3](https://md.research.elamur.ai/free/en/papers/wang-2025-internvl3-5-advancing-open/). 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265.
33. Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, and Haobo Wang. 2025a. Realhitbench: A comprehensive realistic hierarchical table benchmark for evaluating llm-based table analysis. In Findings of the Associatio… [find](https://scholar.google.com/scholar?q=Pengzuo+Wu%2C+Yuhang+Yang%2C+Guangcheng+Zhu%2C+Chao+Ye%2C+Hong+Gu%2C+Xu+Lu%2C+Ruixuan+Xiao%2C+Bowen+Bao%2C+Yijing+He%2C+Liangyu+Zha%2C+Wentao+Ye%2C+Junbo+Zhao%2C+and+Haobo+Wang%2E+2025a%2E+Realhitbench%3A+A+comprehensive+realistic)
34. Zonghan Wu, Junlin Wang, Congyuan Zou, Chenhan Wang, and Yilei Shao. 2025b. Towards competent AI for fundamental analysis in finance: A benchmark dataset and evaluation. CoRR, abs/2506.07315. — [arXiv:2506.07315](https://arxiv.org/abs/2506.07315) [find](https://scholar.google.com/scholar?q=Zonghan+Wu%2C+Junlin+Wang%2C+Congyuan+Zou%2C+Chenhan+Wang%2C+and+Yilei+Shao%2E+2025b%2E+Towards+competent+AI+for+fundamental+analysis+in+finance%3A+A+benchmark+dataset+and+evaluation%2E+CoRR%2C+abs%2F2506%2E07315%2E+%E2%80%94+%5BarXiv)
35. Xiao Yang, Kai Sun, Hao Xin, Yushi Sun, Nikita Bhalla, Xiangsen Chen, Sajal Choudhary, Rongze D Gui, Ziran W Jiang, Ziyu Jiang, and 1 others. 2024. Crag-comprehensive rag benchmark. Advances in Neural Information Processing Systems, 37:10470–10490. [find](https://scholar.google.com/scholar?q=Xiao+Yang%2C+Kai+Sun%2C+Hao+Xin%2C+Yushi+Sun%2C+Nikita+Bhalla%2C+Xiangsen+Chen%2C+Sajal+Choudhary%2C+Rongze+D+Gui%2C+Ziran+W+Jiang%2C+Ziyu+Jiang%2C+and+1+others%2E+2024%2E+Crag%2Dcomprehensive+rag+benchmark%2E+Advances+in+Neural)
36. Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, and Maosong Sun. 2025a. Visrag: Vision-based retrieval-augmented generation on multi-modality documents. In The Thirteenth International Conference on Learning Representations, ICLR 2025,… [find](https://scholar.google.com/scholar?q=Shi+Yu%2C+Chaoyue+Tang%2C+Bokai+Xu%2C+Junbo+Cui%2C+Junhao+Ran%2C+Yukun+Yan%2C+Zhenghao+Liu%2C+Shuo+Wang%2C+Xu+Han%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2025a%2E+Visrag%3A+Vision%2Dbased+retrieval%2Daugmented+generation+on+multi%2Dmod)
37. Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, Wenshuo Ma, Zhihui He, Tianchi Cai, Weize Chen, Yuxiang Huang, Yuanqian Zhao, and 1 others. 2025b. [Minicpm-v 4.5: Cooking efficient mllms via architecture, data, and training recipe](https://md.research.elamur.ai/free/en/papers/yu-2025-minicpm-v-4-5/). arXiv preprint arXiv:2509.18154.
38. Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, and Junbo Zhao. 2025. LeTS: Learning to think-and-search via process-and-outcome reward hybridization. In Proceedings of the 2025 Conference on Empirical Methods in Natural Langu… [find](https://scholar.google.com/scholar?q=Qi+Zhang%2C+Shouqing+Yang%2C+Lirong+Gao%2C+Hao+Chen%2C+Xiaomeng+Hu%2C+Jinglei+Chen%2C+Jiexiang+Wang%2C+Sheng+Guo%2C+Bo+Zheng%2C+Haobo+Wang%2C+and+Junbo+Zhao%2E+2025%2E+LeTS%3A+Learning+to+think%2Dand%2Dsearch+via+process%2Dand%2Doutco)
39. Xin Zhang, Yanzhao Zhang, Wen Xie, Mingxin Li, Ziqi Dai, Dingkun Long, Pengjun Xie, Meishan Zhang, Wenjie Li, and Min Zhang. 2024. Gme: Improving universal multimodal retrieval by multimodal llms. arXiv preprint arXiv:2412.16855. — [arXiv:2412.16855](https://arxiv.org/abs/2412.16855) [find](https://scholar.google.com/scholar?q=Xin+Zhang%2C+Yanzhao+Zhang%2C+Wen+Xie%2C+Mingxin+Li%2C+Ziqi+Dai%2C+Dingkun+Long%2C+Pengjun+Xie%2C+Meishan+Zhang%2C+Wenjie+Li%2C+and+Min+Zhang%2E+2024%2E+Gme%3A+Improving+universal+multimodal+retrieval+by+multimodal+llms%2E+arX)
40. Suifeng Zhao, Zhuoran Jin, Sujian Li, and Jun Gao. 2025. Finragbench-v: A benchmark for multimodal rag with visual citation in the financial domain. arXiv preprint arXiv:2505.17471. [find](https://scholar.google.com/scholar?q=Suifeng+Zhao%2C+Zhuoran+Jin%2C+Sujian+Li%2C+and+Jun+Gao%2E+2025%2E+Finragbench%2Dv%3A+A+benchmark+for+multimodal+rag+with+visual+citation+in+the+financial+domain%2E+arXiv+preprint+arXiv%3A2505%2E17471%2E)
41. Yilun Zhao, Yunxiang Li, Chenying Li, and Rui Zhang. 2022. [Multihiertt: Numerical reasoning over multi hierarchical tabular and textual data](https://md.research.elamur.ai/free/en/papers/zhao-2022-multihiertt-numerical-reasoning-over-multi/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022…
42. Yilun Zhao, Yitao Long, Tintin Jiang, Chengye Wang, Weiyuan Chen, Hongjun Liu, Xiangru Tang, Yiming Zhang, Chen Zhao, and Arman Cohan. 2024. Findver: Explainable claim verification over long and hybrid-content financial documents. In Proceedings of the 2024 Conference on Empirical Methods in Natural… [find](https://scholar.google.com/scholar?q=Yilun+Zhao%2C+Yitao+Long%2C+Tintin+Jiang%2C+Chengye+Wang%2C+Weiyuan+Chen%2C+Hongjun+Liu%2C+Xiangru+Tang%2C+Yiming+Zhang%2C+Chen+Zhao%2C+and+Arman+Cohan%2E+2024%2E+Findver%3A+Explainable+claim+verification+over+long+and+hybri)

*Updated 2 November 2026*