@inproceedings{an-etal-2024-l,
title = "{L}-Eval: Instituting Standardized Evaluation for Long Context Language Models",
author = "An, Chenxin and
Gong, Shansan and
Zhong, Ming and
Zhao, Xingjian and
Li, Mukai and
Zhang, Jun and
Kong, Lingpeng and
Qiu, Xipeng",
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.776",
pages = "14388--14411",
abstract = "Recently, there has been growing interest in long-context scaling of large language models (LLMs). To facilitate research in this field, we propose L-Eval to institute a more standardized evaluation for Long-Context Language Models (LCLMs) addressing two key aspects: dataset construction and evaluation metrics. On the one hand, we build a new evaluation suite containing 20 sub-tasks, 508 long documents, and more than 2,000 human-labeled query-response pairs including diverse task types, domains, and input length (3k{\textasciitilde}200k tokens). On the other hand, we investigate the effectiveness of evaluation metrics for LCLMs and we show that Length-instruction-enhanced (LIE) evaluation and LLM judges can better correlate with human judgments. We conducted a comprehensive study of 4 popular commercial LLMs and 12 open-source counterparts using the L-Eval benchmark. Our empirical findings offer useful insights into the study of LCLMs and lay the groundwork for the development of a more principled evaluation of these models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="an-etal-2024-l">
<titleInfo>
<title>L-Eval: Instituting Standardized Evaluation for Long Context Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenxin</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shansan</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingjian</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mukai</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingpeng</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</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>Recently, there has been growing interest in long-context scaling of large language models (LLMs). To facilitate research in this field, we propose L-Eval to institute a more standardized evaluation for Long-Context Language Models (LCLMs) addressing two key aspects: dataset construction and evaluation metrics. On the one hand, we build a new evaluation suite containing 20 sub-tasks, 508 long documents, and more than 2,000 human-labeled query-response pairs including diverse task types, domains, and input length (3k~200k tokens). On the other hand, we investigate the effectiveness of evaluation metrics for LCLMs and we show that Length-instruction-enhanced (LIE) evaluation and LLM judges can better correlate with human judgments. We conducted a comprehensive study of 4 popular commercial LLMs and 12 open-source counterparts using the L-Eval benchmark. Our empirical findings offer useful insights into the study of LCLMs and lay the groundwork for the development of a more principled evaluation of these models.</abstract>
<identifier type="citekey">an-etal-2024-l</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.776</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14388</start>
<end>14411</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T L-Eval: Instituting Standardized Evaluation for Long Context Language Models
%A An, Chenxin
%A Gong, Shansan
%A Zhong, Ming
%A Zhao, Xingjian
%A Li, Mukai
%A Zhang, Jun
%A Kong, Lingpeng
%A Qiu, Xipeng
%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 an-etal-2024-l
%X Recently, there has been growing interest in long-context scaling of large language models (LLMs). To facilitate research in this field, we propose L-Eval to institute a more standardized evaluation for Long-Context Language Models (LCLMs) addressing two key aspects: dataset construction and evaluation metrics. On the one hand, we build a new evaluation suite containing 20 sub-tasks, 508 long documents, and more than 2,000 human-labeled query-response pairs including diverse task types, domains, and input length (3k~200k tokens). On the other hand, we investigate the effectiveness of evaluation metrics for LCLMs and we show that Length-instruction-enhanced (LIE) evaluation and LLM judges can better correlate with human judgments. We conducted a comprehensive study of 4 popular commercial LLMs and 12 open-source counterparts using the L-Eval benchmark. Our empirical findings offer useful insights into the study of LCLMs and lay the groundwork for the development of a more principled evaluation of these models.
%U https://aclanthology.org/2024.acl-long.776
%P 14388-14411
Markdown (Informal)
[L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://aclanthology.org/2024.acl-long.776) (An et al., ACL 2024)
ACL
- Chenxin An, Shansan Gong, Ming Zhong, Xingjian Zhao, Mukai Li, Jun Zhang, Lingpeng Kong, and Xipeng Qiu. 2024. L-Eval: Instituting Standardized Evaluation for Long Context Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14388–14411, Bangkok, Thailand. Association for Computational Linguistics.