@inproceedings{yan-etal-2024-predicting,
title = "Predicting Text Preference Via Structured Comparative Reasoning",
author = "Yan, Jing Nathan and
Liu, Tianqi and
Chiu, Justin and
Shen, Jiaming and
Qin, Zhen and
Yu, Yue and
Lakshmanan, Charumathi and
Kurzion, Yair and
Rush, Alexander and
Liu, Jialu and
Bendersky, Michael",
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.541/",
doi = "10.18653/v1/2024.acl-long.541",
pages = "10040--10060",
abstract = "Comparative reasoning plays a crucial role in predicting text preferences; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning, leading to incorrect preference predictions. While approaches like Chain-of-Thought improve accuracy in many settings, they struggle to consistently distinguish the similarities and differences of complex texts. We introduce $SC^2$, a model that prompts LLMs to predict text preferences by generating structured intermediate comparisons. $SC^2$ begins by proposing aspects for comparison, followed by generating textual comparisons under each aspect. We select consistent comparisons with a pairwise comparator that ensures each comparison of a given aspect clearly distinguishes differences between texts, significantly reducing hallucination and improving consistency. Our empirical studies across various NLP tasks, including summarization, retrieval, and automatic rating, demonstrate that $SC^2${\textquoteleft}s enhanced performance in text preference prediction is significant."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2024-predicting">
<titleInfo>
<title>Predicting Text Preference Via Structured Comparative Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="given">Nathan</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianqi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Chiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaming</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charumathi</namePart>
<namePart type="family">Lakshmanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yair</namePart>
<namePart type="family">Kurzion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Rush</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Bendersky</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>Comparative reasoning plays a crucial role in predicting text preferences; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning, leading to incorrect preference predictions. While approaches like Chain-of-Thought improve accuracy in many settings, they struggle to consistently distinguish the similarities and differences of complex texts. We introduce SC², a model that prompts LLMs to predict text preferences by generating structured intermediate comparisons. SC² begins by proposing aspects for comparison, followed by generating textual comparisons under each aspect. We select consistent comparisons with a pairwise comparator that ensures each comparison of a given aspect clearly distinguishes differences between texts, significantly reducing hallucination and improving consistency. Our empirical studies across various NLP tasks, including summarization, retrieval, and automatic rating, demonstrate that SC²‘s enhanced performance in text preference prediction is significant.</abstract>
<identifier type="citekey">yan-etal-2024-predicting</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.541</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.541/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10040</start>
<end>10060</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Text Preference Via Structured Comparative Reasoning
%A Yan, Jing Nathan
%A Liu, Tianqi
%A Chiu, Justin
%A Shen, Jiaming
%A Qin, Zhen
%A Yu, Yue
%A Lakshmanan, Charumathi
%A Kurzion, Yair
%A Rush, Alexander
%A Liu, Jialu
%A Bendersky, Michael
%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 yan-etal-2024-predicting
%X Comparative reasoning plays a crucial role in predicting text preferences; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning, leading to incorrect preference predictions. While approaches like Chain-of-Thought improve accuracy in many settings, they struggle to consistently distinguish the similarities and differences of complex texts. We introduce SC², a model that prompts LLMs to predict text preferences by generating structured intermediate comparisons. SC² begins by proposing aspects for comparison, followed by generating textual comparisons under each aspect. We select consistent comparisons with a pairwise comparator that ensures each comparison of a given aspect clearly distinguishes differences between texts, significantly reducing hallucination and improving consistency. Our empirical studies across various NLP tasks, including summarization, retrieval, and automatic rating, demonstrate that SC²‘s enhanced performance in text preference prediction is significant.
%R 10.18653/v1/2024.acl-long.541
%U https://aclanthology.org/2024.luhme-long.541/
%U https://doi.org/10.18653/v1/2024.acl-long.541
%P 10040-10060
Markdown (Informal)
[Predicting Text Preference Via Structured Comparative Reasoning](https://aclanthology.org/2024.luhme-long.541/) (Yan et al., ACL 2024)
ACL
- Jing Nathan Yan, Tianqi Liu, Justin Chiu, Jiaming Shen, Zhen Qin, Yue Yu, Charumathi Lakshmanan, Yair Kurzion, Alexander Rush, Jialu Liu, and Michael Bendersky. 2024. Predicting Text Preference Via Structured Comparative Reasoning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10040–10060, Bangkok, Thailand. Association for Computational Linguistics.