@inproceedings{zhiyu-etal-2024-enhancing,
title = "Enhancing Free-Form Table Question Answering Models by Distilling Relevant-Cell-Based Rationales",
author = "Zhiyu, Yang and
Shuo, Wang and
Yukun, Yan and
Pengyuan, Liu and
Dong, Yu",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.75/",
pages = "973--985",
language = "eng",
abstract = "{\textquotedblleft}Free-form table question answering is a challenging task since tables contain structured contentscompared to plain texts, which requires high-level reasoning abilities to effectively identify cellsthat are relevant to the question and produce a correct and faithful answer based on their relations.Large language models (LLMs) have exhibited remarkable reasoning capabilities in numerousNLP applications. However, in some specific tasks, specially-trained small models can still out-perform LLMs. Furthermore, small models require extremely less computation costs comparedto LLMs. To leverage the strengths of both types of models, we propose a Relevant-Cell-basedKnowledge Distillation with inference-time Teacher Guidance (RCKD-TG) method. This ap-proach aims to combine small free-form table question answering models' abilities to learn fromhuman annotations and large language models' abilities to effectively reason from table contents,via applying Relevant-Cell-based rationales distilled from LLMs to small models' training andinference stages. Our experiments demonstrate the superiority of our method over vanilla smallmodels in correctness, faithfulness, adequacy and fluency, also over general LLMs in adheringto the style of human annotations. We achieve state-of-the-art performance on FeTaQA, a rep-resentative free-form table question answering benchmark. Our result of a 41.3 BLEU scoredemonstrates the feasibility of effectively using small models' task-specific abilities and LLMs`reasoning capabilities at the same time. Additionally, our method exhibits high computation ef-ficiency and data efficiency. Compared to strong baselines, we achieve better performance withsignificantly less training data.{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhiyu-etal-2024-enhancing">
<titleInfo>
<title>Enhancing Free-Form Table Question Answering Models by Distilling Relevant-Cell-Based Rationales</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhiyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Shuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Yukun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Pengyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Free-form table question answering is a challenging task since tables contain structured contentscompared to plain texts, which requires high-level reasoning abilities to effectively identify cellsthat are relevant to the question and produce a correct and faithful answer based on their relations.Large language models (LLMs) have exhibited remarkable reasoning capabilities in numerousNLP applications. However, in some specific tasks, specially-trained small models can still out-perform LLMs. Furthermore, small models require extremely less computation costs comparedto LLMs. To leverage the strengths of both types of models, we propose a Relevant-Cell-basedKnowledge Distillation with inference-time Teacher Guidance (RCKD-TG) method. This ap-proach aims to combine small free-form table question answering models’ abilities to learn fromhuman annotations and large language models’ abilities to effectively reason from table contents,via applying Relevant-Cell-based rationales distilled from LLMs to small models’ training andinference stages. Our experiments demonstrate the superiority of our method over vanilla smallmodels in correctness, faithfulness, adequacy and fluency, also over general LLMs in adheringto the style of human annotations. We achieve state-of-the-art performance on FeTaQA, a rep-resentative free-form table question answering benchmark. Our result of a 41.3 BLEU scoredemonstrates the feasibility of effectively using small models’ task-specific abilities and LLMs‘reasoning capabilities at the same time. Additionally, our method exhibits high computation ef-ficiency and data efficiency. Compared to strong baselines, we achieve better performance withsignificantly less training data.”</abstract>
<identifier type="citekey">zhiyu-etal-2024-enhancing</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.75/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>973</start>
<end>985</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Free-Form Table Question Answering Models by Distilling Relevant-Cell-Based Rationales
%A Zhiyu, Yang
%A Shuo, Wang
%A Yukun, Yan
%A Pengyuan, Liu
%A Dong, Yu
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G eng
%F zhiyu-etal-2024-enhancing
%X “Free-form table question answering is a challenging task since tables contain structured contentscompared to plain texts, which requires high-level reasoning abilities to effectively identify cellsthat are relevant to the question and produce a correct and faithful answer based on their relations.Large language models (LLMs) have exhibited remarkable reasoning capabilities in numerousNLP applications. However, in some specific tasks, specially-trained small models can still out-perform LLMs. Furthermore, small models require extremely less computation costs comparedto LLMs. To leverage the strengths of both types of models, we propose a Relevant-Cell-basedKnowledge Distillation with inference-time Teacher Guidance (RCKD-TG) method. This ap-proach aims to combine small free-form table question answering models’ abilities to learn fromhuman annotations and large language models’ abilities to effectively reason from table contents,via applying Relevant-Cell-based rationales distilled from LLMs to small models’ training andinference stages. Our experiments demonstrate the superiority of our method over vanilla smallmodels in correctness, faithfulness, adequacy and fluency, also over general LLMs in adheringto the style of human annotations. We achieve state-of-the-art performance on FeTaQA, a rep-resentative free-form table question answering benchmark. Our result of a 41.3 BLEU scoredemonstrates the feasibility of effectively using small models’ task-specific abilities and LLMs‘reasoning capabilities at the same time. Additionally, our method exhibits high computation ef-ficiency and data efficiency. Compared to strong baselines, we achieve better performance withsignificantly less training data.”
%U https://aclanthology.org/2024.ccl-1.75/
%P 973-985
Markdown (Informal)
[Enhancing Free-Form Table Question Answering Models by Distilling Relevant-Cell-Based Rationales](https://aclanthology.org/2024.ccl-1.75/) (Zhiyu et al., CCL 2024)
ACL