FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing

arXiv:2610.19240v1 Announce Type: new Abstract: Financial disclosures express the underlying relationships of double-entry accounting through unstructured text. While financial LLM benchmarks predominantly emphasize question answering and classification, schema-guided evidence discovery remains relatively under-explored. We investigate whether open-weight LLMs can extract and classify evidence corresponding to predefined double-entry accounting relationships underlying the text. Using a financial accounting graph comprising 11 nodes (accounts) and 11 edges (transaction types), we evaluate mid-sized models from 5 open-weight families across 1,300 SEC 10-K Item 7 filings spanning 26 years, comparing their extraction performance against three proprietary models. Results reveal substantial differences in extraction volume, edge distributions, and cross-model agreement. Building on this study, we introduce a human-annotated relation classification benchmark comprising 483 passages across three financial accounting categories, evaluating 34 open-weight and 10 proprietary models. The strongest open-weight and proprietary models achieve 84.1\% and 92.8\% accuracy, respectively, with considerable variation across accounting categories. Our findings highlight the importance of evaluating evidence discovery and relation understanding separately, while investigating locally deployable models for scalable, privacy-sensitive financial analysis.

Abstract:Financial disclosures express the underlying relationships of double-entry accounting through unstructured text. While financial LLM benchmarks predominantly emphasize question answering and classification, schema-guided evidence discovery remains relatively under-explored. We investigate whether open-weight LLMs can extract and classify evidence corresponding to predefined double-entry accounting relationships underlying the text. Using a financial accounting graph comprising 11 nodes (accounts) and 11 edges (transaction types), we evaluate mid-sized models from 5 open-weight families across 1,300 SEC 10-K Item 7 filings spanning 26 years, comparing their extraction performance against three proprietary models. Results reveal substantial differences in extraction volume, edge distributions, and cross-model agreement. Building on this study, we introduce a human-annotated relation classification benchmark comprising 483 passages across three financial accounting categories, evaluating 34 open-weight and 10 proprietary models. The strongest open-weight and proprietary models achieve 84.1\% and 92.8\% accuracy, respectively, with considerable variation across accounting categories. Our findings highlight the importance of evaluating evidence discovery and relation understanding separately, while investigating locally deployable models for scalable, privacy-sensitive financial analysis.

Machine Learning (cs.LG)

arXiv:2610.19240 [cs.LG]

(or arXiv:2610.19240v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.19240 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing

Subiecte conexe