@inproceedings{li-etal-2025-towards-better,
title = "Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness",
author = "Li, Jiachun and
Cao, Pengfei and
Chen, Yubo and
Xu, Jiexin and
Li, Huaijun and
Jiang, Xiaojian and
Liu, Kang and
Zhao, Jun",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.560/",
doi = "10.18653/v1/2025.findings-acl.560",
pages = "10747--10765",
ISBN = "979-8-89176-256-5",
abstract = "Chain-of-thought (CoT) prompting demonstrates varying performance under different reasoning tasks.Previous work attempts to evaluate it but falls short in providing an in-depth analysis of patterns that influence the CoT. In this paper, we study the CoT performance from the perspective of effectiveness and faithfulness. For the former, we identify key factors that influence CoT effectiveness on performance improvement, including problem difficulty, information gain, and information flow. For the latter, we interpret the unfaithful CoT issue by conducting a joint analysis of the information interaction among the question, CoT, and answer. The result demonstrates that, when the LLM predicts answers, it can recall correct information missing in the CoT from the question, leading to the problem. Finally, we propose a novel algorithm to mitigate this issue, in which we recall extra information from the question to enhance the CoT generation and evaluate CoTs based on their information gain. Extensive experiments demonstrate that our approach enhances both the faithfulness and effectiveness of CoT."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-towards-better">
<titleInfo>
<title>Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiachun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiexin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huaijun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojian</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Chain-of-thought (CoT) prompting demonstrates varying performance under different reasoning tasks.Previous work attempts to evaluate it but falls short in providing an in-depth analysis of patterns that influence the CoT. In this paper, we study the CoT performance from the perspective of effectiveness and faithfulness. For the former, we identify key factors that influence CoT effectiveness on performance improvement, including problem difficulty, information gain, and information flow. For the latter, we interpret the unfaithful CoT issue by conducting a joint analysis of the information interaction among the question, CoT, and answer. The result demonstrates that, when the LLM predicts answers, it can recall correct information missing in the CoT from the question, leading to the problem. Finally, we propose a novel algorithm to mitigate this issue, in which we recall extra information from the question to enhance the CoT generation and evaluate CoTs based on their information gain. Extensive experiments demonstrate that our approach enhances both the faithfulness and effectiveness of CoT.</abstract>
<identifier type="citekey">li-etal-2025-towards-better</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.560</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.560/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>10747</start>
<end>10765</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness
%A Li, Jiachun
%A Cao, Pengfei
%A Chen, Yubo
%A Xu, Jiexin
%A Li, Huaijun
%A Jiang, Xiaojian
%A Liu, Kang
%A Zhao, Jun
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F li-etal-2025-towards-better
%X Chain-of-thought (CoT) prompting demonstrates varying performance under different reasoning tasks.Previous work attempts to evaluate it but falls short in providing an in-depth analysis of patterns that influence the CoT. In this paper, we study the CoT performance from the perspective of effectiveness and faithfulness. For the former, we identify key factors that influence CoT effectiveness on performance improvement, including problem difficulty, information gain, and information flow. For the latter, we interpret the unfaithful CoT issue by conducting a joint analysis of the information interaction among the question, CoT, and answer. The result demonstrates that, when the LLM predicts answers, it can recall correct information missing in the CoT from the question, leading to the problem. Finally, we propose a novel algorithm to mitigate this issue, in which we recall extra information from the question to enhance the CoT generation and evaluate CoTs based on their information gain. Extensive experiments demonstrate that our approach enhances both the faithfulness and effectiveness of CoT.
%R 10.18653/v1/2025.findings-acl.560
%U https://aclanthology.org/2025.findings-acl.560/
%U https://doi.org/10.18653/v1/2025.findings-acl.560
%P 10747-10765
Markdown (Informal)
[Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness](https://aclanthology.org/2025.findings-acl.560/) (Li et al., Findings 2025)
ACL
- Jiachun Li, Pengfei Cao, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, and Jun Zhao. 2025. Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness. In Findings of the Association for Computational Linguistics: ACL 2025, pages 10747–10765, Vienna, Austria. Association for Computational Linguistics.