@inproceedings{cao-etal-2024-structeval,
title = "{S}truct{E}val: Deepen and Broaden Large Language Model Assessment via Structured Evaluation",
author = "Cao, Boxi and
Ren, Mengjie and
Lin, Hongyu and
Han, Xianpei and
Zhang, Feng and
Zhan, Junfeng and
Sun, Le",
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",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.314/",
doi = "10.18653/v1/2024.findings-acl.314",
pages = "5300--5318",
abstract = "Evaluation is the baton for the development of large language models. Current evaluations typically employ a single-item assessment paradigm for each atomic test objective, which struggle to discern whether a model genuinely possesses the required capabilities or merely memorizes/guesses the answers to specific questions. To this end, this paper proposes a novel evaluation framework referred to as StructEval. Starting from an atomic test objective, StructEval deepens and broadens the evaluation by conducting a structured assessment across multiple cognitive levels and critical concepts, and therefore offers a comprehensive, robust and consistent evaluations for large language models. Experiments on three widely-used benchmarks demonstrate that StructEval serves as a reliable tool for resisting the risk of data contamination, and reducing the interference of potential biases, thereby providing a more reliable and consistent conclusion regarding model capabilities. Our framework also sheds light on the design of future principled and trustworthy LLM evaluation protocols."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2024-structeval">
<titleInfo>
<title>StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boxi</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengjie</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junfeng</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Sun</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Evaluation is the baton for the development of large language models. Current evaluations typically employ a single-item assessment paradigm for each atomic test objective, which struggle to discern whether a model genuinely possesses the required capabilities or merely memorizes/guesses the answers to specific questions. To this end, this paper proposes a novel evaluation framework referred to as StructEval. Starting from an atomic test objective, StructEval deepens and broadens the evaluation by conducting a structured assessment across multiple cognitive levels and critical concepts, and therefore offers a comprehensive, robust and consistent evaluations for large language models. Experiments on three widely-used benchmarks demonstrate that StructEval serves as a reliable tool for resisting the risk of data contamination, and reducing the interference of potential biases, thereby providing a more reliable and consistent conclusion regarding model capabilities. Our framework also sheds light on the design of future principled and trustworthy LLM evaluation protocols.</abstract>
<identifier type="citekey">cao-etal-2024-structeval</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.314</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.314/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>5300</start>
<end>5318</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation
%A Cao, Boxi
%A Ren, Mengjie
%A Lin, Hongyu
%A Han, Xianpei
%A Zhang, Feng
%A Zhan, Junfeng
%A Sun, Le
%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
%F cao-etal-2024-structeval
%X Evaluation is the baton for the development of large language models. Current evaluations typically employ a single-item assessment paradigm for each atomic test objective, which struggle to discern whether a model genuinely possesses the required capabilities or merely memorizes/guesses the answers to specific questions. To this end, this paper proposes a novel evaluation framework referred to as StructEval. Starting from an atomic test objective, StructEval deepens and broadens the evaluation by conducting a structured assessment across multiple cognitive levels and critical concepts, and therefore offers a comprehensive, robust and consistent evaluations for large language models. Experiments on three widely-used benchmarks demonstrate that StructEval serves as a reliable tool for resisting the risk of data contamination, and reducing the interference of potential biases, thereby providing a more reliable and consistent conclusion regarding model capabilities. Our framework also sheds light on the design of future principled and trustworthy LLM evaluation protocols.
%R 10.18653/v1/2024.findings-acl.314
%U https://aclanthology.org/2024.findings-acl.314/
%U https://doi.org/10.18653/v1/2024.findings-acl.314
%P 5300-5318
Markdown (Informal)
[StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation](https://aclanthology.org/2024.findings-acl.314/) (Cao et al., Findings 2024)
ACL