Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Yan, He, Yueru, Xiang, Ruoyu, Zhao, Jeff
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.05700
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910991778840576
author Wang, Yan
He, Yueru
Xiang, Ruoyu
Zhao, Jeff
author_facet Wang, Yan
He, Yueru
Xiang, Ruoyu
Zhao, Jeff
contents Recent advances in large language models (LLMs) hold great promise for financial applications but introduce critical accuracy and compliance challenges in Digital Regulatory Reporting (DRR). To address these issues, we propose RKEFino1, a regulation knowledge-enhanced financial reasoning model built upon Fino1, fine-tuned with domain knowledge from XBRL, CDM, and MOF. We formulate two QA tasks-knowledge-based and mathematical reasoning-and introduce a novel Numerical NER task covering financial entities in both sentences and tables. Experimental results demonstrate the effectiveness and generalization capacity of RKEFino1 in compliance-critical financial tasks. We have released our model on Hugging Face.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05700
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RKEFino1: A Regulation Knowledge-Enhanced Large Language Model
Wang, Yan
He, Yueru
Xiang, Ruoyu
Zhao, Jeff
Computation and Language
Artificial Intelligence
Recent advances in large language models (LLMs) hold great promise for financial applications but introduce critical accuracy and compliance challenges in Digital Regulatory Reporting (DRR). To address these issues, we propose RKEFino1, a regulation knowledge-enhanced financial reasoning model built upon Fino1, fine-tuned with domain knowledge from XBRL, CDM, and MOF. We formulate two QA tasks-knowledge-based and mathematical reasoning-and introduce a novel Numerical NER task covering financial entities in both sentences and tables. Experimental results demonstrate the effectiveness and generalization capacity of RKEFino1 in compliance-critical financial tasks. We have released our model on Hugging Face.
title RKEFino1: A Regulation Knowledge-Enhanced Large Language Model
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.05700