@inproceedings{zhao-etal-2024-tapera,
title = "{T}a{PERA}: Enhancing Faithfulness and Interpretability in Long-Form Table {QA} by Content Planning and Execution-based Reasoning",
author = "Zhao, Yilun and
Chen, Lyuhao and
Cohan, Arman and
Zhao, Chen",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.692/",
doi = "10.18653/v1/2024.acl-long.692",
pages = "12824--12840",
abstract = "Long-form Table Question Answering (LFTQA) requires systems to generate paragraph long and complex answers to questions over tabular data. While Large language models based systems have made significant progress, it often hallucinates, especially when the task involves complex reasoning over tables. To tackle this issue, we propose a new LLM-based framework, TaPERA, for LFTQA tasks. Our framework uses a modular approach that decomposes the whole process into three sub-modules: 1) QA-based Content Planner that iteratively decomposes the input question into sub-questions; 2) Execution-based Table Reasoner that produces executable Python program for each sub-question; and 3) Answer Generator that generates long-form answer grounded on the program output. Human evaluation results on the FeTaQA and QTSumm datasets indicate that our framework significantly improves strong baselines on both accuracy and truthfulness, as our modular framework is better at table reasoning, and the long-form answer is always consistent with the program output. Our modular design further provides transparency as users are able to interact with our framework by manually changing the content plans."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2024-tapera">
<titleInfo>
<title>TaPERA: Enhancing Faithfulness and Interpretability in Long-Form Table QA by Content Planning and Execution-based Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyuhao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Long-form Table Question Answering (LFTQA) requires systems to generate paragraph long and complex answers to questions over tabular data. While Large language models based systems have made significant progress, it often hallucinates, especially when the task involves complex reasoning over tables. To tackle this issue, we propose a new LLM-based framework, TaPERA, for LFTQA tasks. Our framework uses a modular approach that decomposes the whole process into three sub-modules: 1) QA-based Content Planner that iteratively decomposes the input question into sub-questions; 2) Execution-based Table Reasoner that produces executable Python program for each sub-question; and 3) Answer Generator that generates long-form answer grounded on the program output. Human evaluation results on the FeTaQA and QTSumm datasets indicate that our framework significantly improves strong baselines on both accuracy and truthfulness, as our modular framework is better at table reasoning, and the long-form answer is always consistent with the program output. Our modular design further provides transparency as users are able to interact with our framework by manually changing the content plans.</abstract>
<identifier type="citekey">zhao-etal-2024-tapera</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.692</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.692/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12824</start>
<end>12840</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TaPERA: Enhancing Faithfulness and Interpretability in Long-Form Table QA by Content Planning and Execution-based Reasoning
%A Zhao, Yilun
%A Chen, Lyuhao
%A Cohan, Arman
%A Zhao, Chen
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhao-etal-2024-tapera
%X Long-form Table Question Answering (LFTQA) requires systems to generate paragraph long and complex answers to questions over tabular data. While Large language models based systems have made significant progress, it often hallucinates, especially when the task involves complex reasoning over tables. To tackle this issue, we propose a new LLM-based framework, TaPERA, for LFTQA tasks. Our framework uses a modular approach that decomposes the whole process into three sub-modules: 1) QA-based Content Planner that iteratively decomposes the input question into sub-questions; 2) Execution-based Table Reasoner that produces executable Python program for each sub-question; and 3) Answer Generator that generates long-form answer grounded on the program output. Human evaluation results on the FeTaQA and QTSumm datasets indicate that our framework significantly improves strong baselines on both accuracy and truthfulness, as our modular framework is better at table reasoning, and the long-form answer is always consistent with the program output. Our modular design further provides transparency as users are able to interact with our framework by manually changing the content plans.
%R 10.18653/v1/2024.acl-long.692
%U https://aclanthology.org/2024.luhme-long.692/
%U https://doi.org/10.18653/v1/2024.acl-long.692
%P 12824-12840
Markdown (Informal)
[TaPERA: Enhancing Faithfulness and Interpretability in Long-Form Table QA by Content Planning and Execution-based Reasoning](https://aclanthology.org/2024.luhme-long.692/) (Zhao et al., ACL 2024)
ACL