@inproceedings{yan-etal-2024-refutebench,
title = "{R}efute{B}ench: Evaluating Refuting Instruction-Following for Large Language Models",
author = "Yan, Jianhao and
Luo, Yun and
Zhang, Yue",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.818",
pages = "13775--13791",
abstract = "The application scope of large language models (LLMs) is increasingly expanding. In practical use, users might provide feedback based on the model{'}s output, hoping for a responsive model that can complete responses according to their feedback. Whether the model can appropriately respond to users{'} refuting feedback and consistently follow through with execution has not been thoroughly analyzed. In light of this, this paper proposes a comprehensive benchmark, \textbf{RefuteBench}, covering tasks such as question answering, machine translation, and email writing. The evaluation aims to assess whether models can positively accept feedback in form of refuting instructions and whether they can consistently adhere to user demands throughout the conversation. We conduct evaluations on numerous LLMs and find that LLMs are stubborn, i.e. exhibit inclination to their internal knowledge, often failing to comply with user feedback. Additionally, as the length of the conversation increases, models gradually forget the user{'}s stated feedback and roll back to their own responses. We further propose a \textit{recall-and-repeat} prompts as a simple and effective way to enhance the model{'}s responsiveness to feedback.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2024-refutebench">
<titleInfo>
<title>RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianhao</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics ACL 2024</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 and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The application scope of large language models (LLMs) is increasingly expanding. In practical use, users might provide feedback based on the model’s output, hoping for a responsive model that can complete responses according to their feedback. Whether the model can appropriately respond to users’ refuting feedback and consistently follow through with execution has not been thoroughly analyzed. In light of this, this paper proposes a comprehensive benchmark, RefuteBench, covering tasks such as question answering, machine translation, and email writing. The evaluation aims to assess whether models can positively accept feedback in form of refuting instructions and whether they can consistently adhere to user demands throughout the conversation. We conduct evaluations on numerous LLMs and find that LLMs are stubborn, i.e. exhibit inclination to their internal knowledge, often failing to comply with user feedback. Additionally, as the length of the conversation increases, models gradually forget the user’s stated feedback and roll back to their own responses. We further propose a recall-and-repeat prompts as a simple and effective way to enhance the model’s responsiveness to feedback.</abstract>
<identifier type="citekey">yan-etal-2024-refutebench</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.818</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13775</start>
<end>13791</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models
%A Yan, Jianhao
%A Luo, Yun
%A Zhang, Yue
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F yan-etal-2024-refutebench
%X The application scope of large language models (LLMs) is increasingly expanding. In practical use, users might provide feedback based on the model’s output, hoping for a responsive model that can complete responses according to their feedback. Whether the model can appropriately respond to users’ refuting feedback and consistently follow through with execution has not been thoroughly analyzed. In light of this, this paper proposes a comprehensive benchmark, RefuteBench, covering tasks such as question answering, machine translation, and email writing. The evaluation aims to assess whether models can positively accept feedback in form of refuting instructions and whether they can consistently adhere to user demands throughout the conversation. We conduct evaluations on numerous LLMs and find that LLMs are stubborn, i.e. exhibit inclination to their internal knowledge, often failing to comply with user feedback. Additionally, as the length of the conversation increases, models gradually forget the user’s stated feedback and roll back to their own responses. We further propose a recall-and-repeat prompts as a simple and effective way to enhance the model’s responsiveness to feedback.
%U https://aclanthology.org/2024.findings-acl.818
%P 13775-13791
Markdown (Informal)
[RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models](https://aclanthology.org/2024.findings-acl.818) (Yan et al., Findings 2024)
ACL