Elamur Research⌕
☰
home / papers / 2026 / MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022–2025)

MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022–2025)

Paper · 2026 · Paolo Pedinotti, Peter Baumann, Nathan Jessurun et al.

Summary

Since ChatGPT appeared, research on generative AI in finance has grown faster than narrative surveys can track. The authors present MetaGraph, a reusable pipeline that converts a scientific corpus into a typed knowledge graph so that trends can be measured rather than described. They assembled 681 Financial NLP papers (2022–2025) from ACL Anthology and arXiv using keyword filtering followed by manual screening. The papers were OCR-ed with Mistral OCR, and Gemini 2.5 Flash extracted entities under a hand-built ontology: tasks, datasets, models, techniques, motivations, limitations, and authors and institutions. Embedding-based entity merging and LLM-assisted taxonomy induction followed. Querying the resulting graph shows three stages. First came an LLM-fuelled growth in tasks and datasets, with financial QA rising. Attention then moved toward limitations, safety, and risk. Most recently, work has shifted to modular systems built around retrieval and agents. Industry adopted these changes faster than academia. The released graph supports reproducible monitoring of the field, and the method could be applied to other domains.

Key points

  • Corpus: 681 papers drawn from ACL Anthology and arXiv (cs.CL and q-fin categories), split into three roughly equal periods (T1–T3) for temporal comparison.
  • Pipeline: Mistral OCR, then schema-constrained extraction with Gemini 2.5 Flash, then entity merging with OpenAI text-embedding-small at a cosine threshold of 0.93. A check on 12 gold papers found minor omissions and no hallucinations.
  • Shift toward system-level methods: papers using RAG went from 39 to 65 to 92 across the periods, and agent-based work from 9 to 25 to 40. Chunk-level retrieval rose from about 85% to 95% of RAG setups.
  • Reported limitations moved away from data scarcity and toward model- and safety-related risks, such as stock or product bias, sensitive-data leaks, and regulatory misreading.
  • The knowledge graph is released on Zenodo (record 16,968,876). Material from 58 papers was withheld because of CC-BY-NC-ND licensing.

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

 Fields, topics and concepts

📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSocial Sciences · 1,772 worksBiochemistry, Genetics and Molecular Biology · 234 worksMolecular Biology · 231 worksGeneral Social Sciences · 227 works

Cite

Cite as Paolo Pedinotti, Peter Baumann, Nathan Jessurun, Leslie Barrett and Enrico Santus. 2026. MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022–2025). Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.gem-main.71

@inproceedings{pedinotti2026metagraph,
  title = {{MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022–2025)}},
  author = {Paolo Pedinotti, Peter Baumann, Nathan Jessurun, Leslie Barrett and Enrico Santus},
  booktitle = {Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)},
  year = {2026},
  doi = {10.18653/v1/2026.gem-main.71},
  url = {https://doi.org/10.18653/v1/2026.gem-main.71}
}

References

29 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Yuemin Chen, Feifan Wu, Jingwei Wang, Hao Qian, Ziqi Liu, Zhiqiang Zhang, Jun Zhou, and Meng Wang. 2024. Knowledge-augmented financial market analysis and report generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1207–1217, Mi… find
  2. Despite continuous human validation and refinement, the entity extraction and taxonomy induction processes remain based on LLMs, Hamed Babaei Giglou, Jennifer D’Souza, and Sören Auer. 2023. Llms4ol: Large language models for ontology learning. In The Semantic Web – ISWC 2023, pages 408–427, Cham. Sp… find
  3. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, and 29 others. 2023. Qwen technical report. Preprint, arXiv:2309.16609.
  4. Salvatore Carta, Alessandro Giuliani, Leonardo Piano, Alessandro Sebastian Podda, Livio Pompianu, and Sandro Gabriele Tiddia. 2023. Iterative zero-shot llm prompting for knowledge graph construction. Preprint, arXiv:2307.01128. — [arXiv:2307.01128](https://arxiv.org/abs/2307.01128) find
  5. Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan Routledge, and William Yang Wang. 2021. FinQA: A dataset of numerical reasoning over financial data. In Proceedings of the 2021 Conference on Empirical Methods in Natural…
  6. Zhiyu Chen, Shiyang Li, Charese Smiley, Zhiqiang Ma, Sameena Shah, and William Yang Wang. 2022. ConvFinQA: Exploring the chain of numerical reasoning in conversational finance question answering. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6279– 6…
  7. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  8. Kelvin Du, Yazhi Zhao, Rui Mao, Frank Xing, and Erik Cambria. 2025. Natural language processing in finance: A survey. Information Fusion, 115:102755. find
  9. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2025. From local to global: A graph rag approach to query-focused summarization. Preprint, arXiv:2404.16130. find
  10. Maurice Funk, Simon Hosemann, Jean Christoph Jung, and Carsten Lutz. 2023. Towards ontology construction with language models. In Joint proceedings of the 1st workshop on Knowledge Base Construction from Pre-Trained Language Models (KBC-LM) and the 2nd challenge on Language Models for Knowledge Base…
  11. 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. ArXiv, abs/2312.10997.
  12. Yue Guo and Yi Yang. 2024. EconNLI: Evaluating large language models on economics reasoning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 982–994, Bangkok, Thailand. Association for Computational Linguistics. find
  13. Pranab Islam, Anand Kannappan, Douwe Kiela, Rebecca Qian, Nino Scherrer, and Bertie Vidgen. 2023. Financebench: A new benchmark for financial question answering. Preprint, arXiv:2311.11944. — [arXiv:2311.11944](https://arxiv.org/abs/2311.11944) find
  14. Simerjot Kaur, Charese Smiley, Akshat Gupta, Joy Sain, Dongsheng Wang, Suchetha Siddagangappa, Toyin Aguda, and Sameena Shah. 2023. Refind: Relation extraction financial dataset. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR… find
  15. 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
  16. Jiangtong Li, Yuxuan Bian, Guoxuan Wang, Yang Lei, Dawei Cheng, Zhijun Ding, and Changjun Jiang. 2023a. Cfgpt: Chinese financial assistant with large language model. Preprint, arXiv:2309.10654. — [arXiv:2309.10654](https://arxiv.org/abs/2309.10654) find
  17. Xiang Li, Zhenyu Li, Chen Shi, Yong Xu, Qing Du, Mingkui Tan, and Jun Huang. 2024. AlphaFin: Benchmarking financial analysis with retrieval-augmented stock-chain framework. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC… find
  18. Yinheng Li, Shaofei Wang, Han Ding, and Hang Chen. 2023b. Large language models in finance: A survey. arXiv preprint arXiv:2311.10723. Accepted at the 4th ACM International Conference on AI in Finance (ICAIF-23). — [arXiv:2311.10723](https://arxiv.org/abs/2311.10723) find
  19. Jiaxin Liu, Yi Yang, and Kar Yan Tam. 2025. Evaluating and aligning human economic risk preferences in llms. Preprint, arXiv:2503.06646. find
  20. Macedo Maia, Siegfried Handschuh, André Freitas, Brian Davis, Ross McDermott, Manel Zarrouk, and Alexandra Balahur. 2018. Www’18 open challenge: Financial opinion mining and question answering. In Companion Proceedings of the The Web Conference 2018, WWW ’18, page 1941–1942, Republic and Canton of G… find
  21. Pekka Malo, Ankur Sinha, Pekka Korhonen, Jyrki Wallenius, and Pyry Takala. 2014. Good debt or bad debt: Detecting semantic orientations in economic texts. Journal of the Association for Information Science and Technology, 65(4):782–796. find
  22. Yuqi Nie, Yaxuan Kong, Xiaowen Dong, John M. Mulvey, H. Vincent Poor, Qingsong Wen, and Stefan Zohren. 2024. A survey of large language models for financial applications: Progress, prospects and challenges. Preprint, arXiv:2406.11903. — [arXiv:2406.11903](https://arxiv.org/abs/2406.11903) find
  23. Sander Schulhoff, Michael Ilie, Nishant Balepur, Konstantine Kahadze, Amanda Liu, Chenglei Si, Yinheng Li, Aayush Gupta, HyoJung Han, Sevien Schulhoff, Pranav Sandeep Dulepet, Saurav Vidyadhara, Dayeon Ki, Sweta Agrawal, Chau Pham, Gerson Kroiz, Feileen Li, Hudson Tao, Ashay Srivastava, and reflecti… — The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
  24. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. Preprint…
  25. Frank Z. Xing, Erik Cambria, and Roy E. Welsch. 2018. Natural language based financial forecasting: a survey. Artificial Intelligence Review, 50(1):49–73. find
  26. Siqiao Xue, Fan Zhou, Yi Xu, Ming Jin, Qingsong Wen, Hongyan Hao, Qingyang Dai, Caigao Jiang, Hongyu Zhao, Shuo Xie, Jianshan He, James Zhang, and Hongyuan Mei. 2024. Weaverbird: Empowering financial decision-making with large language model, knowledge base, and search engine. Preprint, arXiv:2308.0… — [arXiv:2308.05361](https://arxiv.org/abs/2308.05361) find
  27. Antonio Jimeno Yepes, Yao You, Jan Milczek, Sebastian Laverde, and Renyu Li. 2024. Financial report chunking for effective retrieval augmented generation. Preprint, arXiv:2402.05131. — [arXiv:2402.05131](https://arxiv.org/abs/2402.05131) find
  28. Boyu Zhang, Hongyang Yang, Tianyu Zhou, Muhammad Ali Babar, and Xiao-Yang Liu. 2023. Enhancing financial sentiment analysis via retrieval augmented large language models. In Proceedings of the Fourth ACM International Conference on AI in Finance, ICAIF ’23, page 349–356, New York, NY, USA. Associati… find
  29. Yiyun Zhao, Prateek Singh, Hanoz Bhathena, Bernardo Ramos, Aviral Joshi, Swaroop Gadiyaram, and Saket Sharma. 2024. Optimizing LLM based retrieval augmented generation pipelines in the financial domain. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Comput… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/pedinotti-2026-metagraph-large-scale-meta-analysis/