@inproceedings{dong-etal-2024-bamboo,
title = "{BAMBOO}: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models",
author = "Dong, Zican and
Tang, Tianyi and
Li, Junyi and
Zhao, Wayne Xin and
Wen, Ji-Rong",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.188",
pages = "2086--2099",
abstract = "Large language models (LLMs) have achieved dramatic proficiency over NLP tasks with normal length. Recently, multiple studies have committed to extending the context length and enhancing the long text modeling capabilities of LLMs. To comprehensively evaluate the long context ability of LLMs, we propose BAMBOO, a multi-task long context benchmark. BAMBOO has been designed with four principles: comprehensive capacity evaluation, avoidance of data contamination, accurate automatic evaluation, and different length levels. It consists of 10 datasets from 5 different long text understanding tasks, i.e., question answering, hallucination detection, text sorting, language modeling, and code completion, to cover various domains and core capacities of LLMs. We conduct experiments with five widely-used long-context models and further discuss five key questions for long text research. In the end, we discuss problems of current long-context models and point out future directions for enhancing long text modeling capacities. We release our data, prompts, and code at https://anonymous.4open.science/r/BAMBOO/.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2024-bamboo">
<titleInfo>
<title>BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zican</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wayne</namePart>
<namePart type="given">Xin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji-Rong</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have achieved dramatic proficiency over NLP tasks with normal length. Recently, multiple studies have committed to extending the context length and enhancing the long text modeling capabilities of LLMs. To comprehensively evaluate the long context ability of LLMs, we propose BAMBOO, a multi-task long context benchmark. BAMBOO has been designed with four principles: comprehensive capacity evaluation, avoidance of data contamination, accurate automatic evaluation, and different length levels. It consists of 10 datasets from 5 different long text understanding tasks, i.e., question answering, hallucination detection, text sorting, language modeling, and code completion, to cover various domains and core capacities of LLMs. We conduct experiments with five widely-used long-context models and further discuss five key questions for long text research. In the end, we discuss problems of current long-context models and point out future directions for enhancing long text modeling capacities. We release our data, prompts, and code at https://anonymous.4open.science/r/BAMBOO/.</abstract>
<identifier type="citekey">dong-etal-2024-bamboo</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.188</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2086</start>
<end>2099</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models
%A Dong, Zican
%A Tang, Tianyi
%A Li, Junyi
%A Zhao, Wayne Xin
%A Wen, Ji-Rong
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F dong-etal-2024-bamboo
%X Large language models (LLMs) have achieved dramatic proficiency over NLP tasks with normal length. Recently, multiple studies have committed to extending the context length and enhancing the long text modeling capabilities of LLMs. To comprehensively evaluate the long context ability of LLMs, we propose BAMBOO, a multi-task long context benchmark. BAMBOO has been designed with four principles: comprehensive capacity evaluation, avoidance of data contamination, accurate automatic evaluation, and different length levels. It consists of 10 datasets from 5 different long text understanding tasks, i.e., question answering, hallucination detection, text sorting, language modeling, and code completion, to cover various domains and core capacities of LLMs. We conduct experiments with five widely-used long-context models and further discuss five key questions for long text research. In the end, we discuss problems of current long-context models and point out future directions for enhancing long text modeling capacities. We release our data, prompts, and code at https://anonymous.4open.science/r/BAMBOO/.
%U https://aclanthology.org/2024.lrec-main.188
%P 2086-2099
Markdown (Informal)
[BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models](https://aclanthology.org/2024.lrec-main.188) (Dong et al., LREC-COLING 2024)
ACL