Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yuxiang, Qi, Jianzhong, Gan, Junhao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911006839537664
author Wang, Yuxiang
Qi, Jianzhong
Gan, Junhao
author_facet Wang, Yuxiang
Qi, Jianzhong
Gan, Junhao
contents Question answering on free-form tables (a.k.a. TableQA) is a challenging task because of the flexible structure and complex schema of tables. Recent studies use Large Language Models (LLMs) for this task, exploiting their capability in understanding the questions and tabular data, which are typically given in natural language and contain many textual fields, respectively. While this approach has shown promising results, it overlooks the challenges brought by numerical values which are common in tabular data, and LLMs are known to struggle with such values. We aim to address this issue, and we propose a model named TabLaP that uses LLMs as a planner rather than an answer generator. This approach exploits LLMs' capability in multi-step reasoning while leaving the actual numerical calculations to a Python interpreter for accurate calculation. Recognizing the inaccurate nature of LLMs, we further make a first attempt to quantify the trustworthiness of the answers produced by TabLaP, such that users can use TabLaP in a regret-aware manner. Experimental results on two benchmark datasets show that TabLaP is substantially more accurate than the state-of-the-art models, improving the answer accuracy by 5.7% and 5.8% on the two datasets, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12846
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering
Wang, Yuxiang
Qi, Jianzhong
Gan, Junhao
Computation and Language
Artificial Intelligence
Question answering on free-form tables (a.k.a. TableQA) is a challenging task because of the flexible structure and complex schema of tables. Recent studies use Large Language Models (LLMs) for this task, exploiting their capability in understanding the questions and tabular data, which are typically given in natural language and contain many textual fields, respectively. While this approach has shown promising results, it overlooks the challenges brought by numerical values which are common in tabular data, and LLMs are known to struggle with such values. We aim to address this issue, and we propose a model named TabLaP that uses LLMs as a planner rather than an answer generator. This approach exploits LLMs' capability in multi-step reasoning while leaving the actual numerical calculations to a Python interpreter for accurate calculation. Recognizing the inaccurate nature of LLMs, we further make a first attempt to quantify the trustworthiness of the answers produced by TabLaP, such that users can use TabLaP in a regret-aware manner. Experimental results on two benchmark datasets show that TabLaP is substantially more accurate than the state-of-the-art models, improving the answer accuracy by 5.7% and 5.8% on the two datasets, respectively.
title Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.12846