@inproceedings{yin-etal-2024-benchmarking,
title = "Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation",
author = "Yin, Xunjian and
Zhang, Xu and
Ruan, Jie and
Wan, Xiaojun",
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.acl-long.124",
pages = "2270--2286",
abstract = "In recent years, substantial advancements have been made in the development of large language models, achieving remarkable performance across diverse tasks.To evaluate the knowledge ability of language models, previous studies have proposed lots of benchmarks based on question-answering pairs.We argue that it is not reliable and comprehensive to evaluate language models with a fixed question or limited paraphrases as the query, since language models are sensitive to prompt.Therefore, we introduce a novel concept named knowledge boundary to encompass both prompt-agnostic and prompt-sensitive knowledge within language models.Knowledge boundary avoids prompt sensitivity in language model evaluations, rendering them more dependable and robust.To explore the knowledge boundary for a given model, we propose projected gradient descent method with semantic constraints, a new algorithm designed to identify the optimal prompt for each piece of knowledge.Experiments demonstrate a superior performance of our algorithm in computing the knowledge boundary compared to existing methods.Furthermore, we evaluate the ability of multiple language models in several domains with knowledge boundary.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2024-benchmarking">
<titleInfo>
<title>Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xunjian</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</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>In recent years, substantial advancements have been made in the development of large language models, achieving remarkable performance across diverse tasks.To evaluate the knowledge ability of language models, previous studies have proposed lots of benchmarks based on question-answering pairs.We argue that it is not reliable and comprehensive to evaluate language models with a fixed question or limited paraphrases as the query, since language models are sensitive to prompt.Therefore, we introduce a novel concept named knowledge boundary to encompass both prompt-agnostic and prompt-sensitive knowledge within language models.Knowledge boundary avoids prompt sensitivity in language model evaluations, rendering them more dependable and robust.To explore the knowledge boundary for a given model, we propose projected gradient descent method with semantic constraints, a new algorithm designed to identify the optimal prompt for each piece of knowledge.Experiments demonstrate a superior performance of our algorithm in computing the knowledge boundary compared to existing methods.Furthermore, we evaluate the ability of multiple language models in several domains with knowledge boundary.</abstract>
<identifier type="citekey">yin-etal-2024-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.124</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2270</start>
<end>2286</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation
%A Yin, Xunjian
%A Zhang, Xu
%A Ruan, Jie
%A Wan, Xiaojun
%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 yin-etal-2024-benchmarking
%X In recent years, substantial advancements have been made in the development of large language models, achieving remarkable performance across diverse tasks.To evaluate the knowledge ability of language models, previous studies have proposed lots of benchmarks based on question-answering pairs.We argue that it is not reliable and comprehensive to evaluate language models with a fixed question or limited paraphrases as the query, since language models are sensitive to prompt.Therefore, we introduce a novel concept named knowledge boundary to encompass both prompt-agnostic and prompt-sensitive knowledge within language models.Knowledge boundary avoids prompt sensitivity in language model evaluations, rendering them more dependable and robust.To explore the knowledge boundary for a given model, we propose projected gradient descent method with semantic constraints, a new algorithm designed to identify the optimal prompt for each piece of knowledge.Experiments demonstrate a superior performance of our algorithm in computing the knowledge boundary compared to existing methods.Furthermore, we evaluate the ability of multiple language models in several domains with knowledge boundary.
%U https://aclanthology.org/2024.acl-long.124
%P 2270-2286
Markdown (Informal)
[Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation](https://aclanthology.org/2024.acl-long.124) (Yin et al., ACL 2024)
ACL