Improved LLM Agents for Financial Document Question Answering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tan, Nelvin, Seng, Zian, Zhang, Liang, Shih, Yu-Ching, Yang, Dong, Salunkhe, Amol
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914236985245696
author Tan, Nelvin
Seng, Zian
Zhang, Liang
Shih, Yu-Ching
Yang, Dong
Salunkhe, Amol
author_facet Tan, Nelvin
Seng, Zian
Zhang, Liang
Shih, Yu-Ching
Yang, Dong
Salunkhe, Amol
contents Large language models (LLMs) have shown impressive capabilities on numerous natural language processing tasks. However, LLMs still struggle with numerical question answering for financial documents that include tabular and textual data. Recent works have showed the effectiveness of critic agents (i.e., self-correction) for this task given oracle labels. Building upon this framework, this paper examines the effectiveness of the traditional critic agent when oracle labels are not available, and show, through experiments, that this critic agent's performance deteriorates in this scenario. With this in mind, we present an improved critic agent, along with the calculator agent which outperforms the previous state-of-the-art approach (program-of-thought) and is safer. Furthermore, we investigate how our agents interact with each other, and how this interaction affects their performance.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08726
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improved LLM Agents for Financial Document Question Answering
Tan, Nelvin
Seng, Zian
Zhang, Liang
Shih, Yu-Ching
Yang, Dong
Salunkhe, Amol
Computation and Language
Artificial Intelligence
Large language models (LLMs) have shown impressive capabilities on numerous natural language processing tasks. However, LLMs still struggle with numerical question answering for financial documents that include tabular and textual data. Recent works have showed the effectiveness of critic agents (i.e., self-correction) for this task given oracle labels. Building upon this framework, this paper examines the effectiveness of the traditional critic agent when oracle labels are not available, and show, through experiments, that this critic agent's performance deteriorates in this scenario. With this in mind, we present an improved critic agent, along with the calculator agent which outperforms the previous state-of-the-art approach (program-of-thought) and is safer. Furthermore, we investigate how our agents interact with each other, and how this interaction affects their performance.
title Improved LLM Agents for Financial Document Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.08726