@inproceedings{wu-etal-2024-instructeval,
title = "{I}nstruct{E}val: Instruction-Tuned Text Evaluator from Human Preference",
author = "Wu, Wenhao and
Li, Wei and
Xiao, Xinyan and
Liu, Jiachen and
Li, Sujian",
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.799",
pages = "13462--13474",
abstract = "This paper explores to construct a general text evaluator based on open-source Large Language Models (LLMs), a domain predominantly occupied by commercial counterparts such as GPT-4. Recognizing the limitations of open-source models like Llama in evaluative tasks, we introduce InstructEval, a general multi-aspect text evaluator developed through instruction tuning of open-source LLMs. To overcome the shortage of annotated resources for multi-aspect evaluations, InstructEval combines extensive open Human Preference Modeling (HPM) datasets with a small set of multi-aspect annotated data.This approach not only enhances effectiveness in overall evaluation tasks but also exhibits improved performance in multi-aspect evaluation tasks.As demonstrated by our extensive experiments, InstructEval achieves comparable or superior performance to commercial LLMs like ChatGPT or GPT-4 in terms of both overall and multi-aspect evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-instructeval">
<titleInfo>
<title>InstructEval: Instruction-Tuned Text Evaluator from Human Preference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyan</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiachen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</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>This paper explores to construct a general text evaluator based on open-source Large Language Models (LLMs), a domain predominantly occupied by commercial counterparts such as GPT-4. Recognizing the limitations of open-source models like Llama in evaluative tasks, we introduce InstructEval, a general multi-aspect text evaluator developed through instruction tuning of open-source LLMs. To overcome the shortage of annotated resources for multi-aspect evaluations, InstructEval combines extensive open Human Preference Modeling (HPM) datasets with a small set of multi-aspect annotated data.This approach not only enhances effectiveness in overall evaluation tasks but also exhibits improved performance in multi-aspect evaluation tasks.As demonstrated by our extensive experiments, InstructEval achieves comparable or superior performance to commercial LLMs like ChatGPT or GPT-4 in terms of both overall and multi-aspect evaluation.</abstract>
<identifier type="citekey">wu-etal-2024-instructeval</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.799</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13462</start>
<end>13474</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InstructEval: Instruction-Tuned Text Evaluator from Human Preference
%A Wu, Wenhao
%A Li, Wei
%A Xiao, Xinyan
%A Liu, Jiachen
%A Li, Sujian
%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 wu-etal-2024-instructeval
%X This paper explores to construct a general text evaluator based on open-source Large Language Models (LLMs), a domain predominantly occupied by commercial counterparts such as GPT-4. Recognizing the limitations of open-source models like Llama in evaluative tasks, we introduce InstructEval, a general multi-aspect text evaluator developed through instruction tuning of open-source LLMs. To overcome the shortage of annotated resources for multi-aspect evaluations, InstructEval combines extensive open Human Preference Modeling (HPM) datasets with a small set of multi-aspect annotated data.This approach not only enhances effectiveness in overall evaluation tasks but also exhibits improved performance in multi-aspect evaluation tasks.As demonstrated by our extensive experiments, InstructEval achieves comparable or superior performance to commercial LLMs like ChatGPT or GPT-4 in terms of both overall and multi-aspect evaluation.
%U https://aclanthology.org/2024.findings-acl.799
%P 13462-13474
Markdown (Informal)
[InstructEval: Instruction-Tuned Text Evaluator from Human Preference](https://aclanthology.org/2024.findings-acl.799) (Wu et al., Findings 2024)
ACL