Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Srivastava, Pragya, Malik, Manuj, Gupta, Vivek, Ganu, Tanuja, Roth, Dan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912638785552384
author Srivastava, Pragya
Malik, Manuj
Gupta, Vivek
Ganu, Tanuja
Roth, Dan
author_facet Srivastava, Pragya
Malik, Manuj
Gupta, Vivek
Ganu, Tanuja
Roth, Dan
contents Large Language Models (LLMs), excel in natural language understanding, but their capability for complex mathematical reasoning with an amalgamation of structured tables and unstructured text is uncertain. This study explores LLMs' mathematical reasoning on four financial tabular question-answering datasets: TATQA, FinQA, ConvFinQA, and Multihiertt. Through extensive experiments with various models and prompting techniques, we assess how LLMs adapt to complex tables and mathematical tasks. We focus on sensitivity to table complexity and performance variations with an increasing number of arithmetic reasoning steps. The results provide insights into LLMs' capabilities and limitations in handling complex mathematical scenarios for semi-structured tables. Ultimately, we introduce a novel prompting technique tailored to semi-structured documents, matching or outperforming other baselines in performance while providing a nuanced understanding of LLMs abilities for such a task.
format Preprint
id arxiv_https___arxiv_org_abs_2402_11194
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering
Srivastava, Pragya
Malik, Manuj
Gupta, Vivek
Ganu, Tanuja
Roth, Dan
Computation and Language
Large Language Models (LLMs), excel in natural language understanding, but their capability for complex mathematical reasoning with an amalgamation of structured tables and unstructured text is uncertain. This study explores LLMs' mathematical reasoning on four financial tabular question-answering datasets: TATQA, FinQA, ConvFinQA, and Multihiertt. Through extensive experiments with various models and prompting techniques, we assess how LLMs adapt to complex tables and mathematical tasks. We focus on sensitivity to table complexity and performance variations with an increasing number of arithmetic reasoning steps. The results provide insights into LLMs' capabilities and limitations in handling complex mathematical scenarios for semi-structured tables. Ultimately, we introduce a novel prompting technique tailored to semi-structured documents, matching or outperforming other baselines in performance while providing a nuanced understanding of LLMs abilities for such a task.
title Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering
topic Computation and Language
url https://arxiv.org/abs/2402.11194