@inproceedings{guo-etal-2024-ctooleval,
title = "{CT}ool{E}val: A {C}hinese Benchmark for {LLM}-Powered Agent Evaluation in Real-World {API} Interactions",
author = "Guo, Zishan and
Huang, Yufei and
Xiong, Deyi",
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.928/",
doi = "10.18653/v1/2024.findings-acl.928",
pages = "15711--15724",
abstract = "Assessing the capabilities of large language models (LLMs) as agents in decision making and operational tasks is crucial for the development of LLM-as-agent service. We propose CToolEval, a benchmark designed to evaluate LLMs in the context of Chinese societal applications, featuring 398 APIs across 27 widely-used Apps (e.g., Apps for shopping, map, music, travel, etc.) that cover 14 domains. We further present an evaluation framework that simulates real-life scenarios, to facilitate the assessment of tool invocation ability of LLMs for tool learning and task completion ability for user interation. Our extensive experiments with CToolEval evaluate 11 LLMs, revealing that while GPT-3.5-turbo excels in tool invocation, Chinese LLMs usually struggle with issues like hallucination and a lack of comprehensive tool understanding. Our findings highlight the need for further refinement in decision-making capabilities of LLMs, offering insights into bridging the gap between current functionalities and agent-level performance. To promote further research for LLMs to fully act as reliable agents in complex, real-world situations, we release our data and codes at https://github.com/tjunlp-lab/CToolEval."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2024-ctooleval">
<titleInfo>
<title>CToolEval: A Chinese Benchmark for LLM-Powered Agent Evaluation in Real-World API Interactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zishan</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</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>Assessing the capabilities of large language models (LLMs) as agents in decision making and operational tasks is crucial for the development of LLM-as-agent service. We propose CToolEval, a benchmark designed to evaluate LLMs in the context of Chinese societal applications, featuring 398 APIs across 27 widely-used Apps (e.g., Apps for shopping, map, music, travel, etc.) that cover 14 domains. We further present an evaluation framework that simulates real-life scenarios, to facilitate the assessment of tool invocation ability of LLMs for tool learning and task completion ability for user interation. Our extensive experiments with CToolEval evaluate 11 LLMs, revealing that while GPT-3.5-turbo excels in tool invocation, Chinese LLMs usually struggle with issues like hallucination and a lack of comprehensive tool understanding. Our findings highlight the need for further refinement in decision-making capabilities of LLMs, offering insights into bridging the gap between current functionalities and agent-level performance. To promote further research for LLMs to fully act as reliable agents in complex, real-world situations, we release our data and codes at https://github.com/tjunlp-lab/CToolEval.</abstract>
<identifier type="citekey">guo-etal-2024-ctooleval</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.928</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.928/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>15711</start>
<end>15724</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CToolEval: A Chinese Benchmark for LLM-Powered Agent Evaluation in Real-World API Interactions
%A Guo, Zishan
%A Huang, Yufei
%A Xiong, Deyi
%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 guo-etal-2024-ctooleval
%X Assessing the capabilities of large language models (LLMs) as agents in decision making and operational tasks is crucial for the development of LLM-as-agent service. We propose CToolEval, a benchmark designed to evaluate LLMs in the context of Chinese societal applications, featuring 398 APIs across 27 widely-used Apps (e.g., Apps for shopping, map, music, travel, etc.) that cover 14 domains. We further present an evaluation framework that simulates real-life scenarios, to facilitate the assessment of tool invocation ability of LLMs for tool learning and task completion ability for user interation. Our extensive experiments with CToolEval evaluate 11 LLMs, revealing that while GPT-3.5-turbo excels in tool invocation, Chinese LLMs usually struggle with issues like hallucination and a lack of comprehensive tool understanding. Our findings highlight the need for further refinement in decision-making capabilities of LLMs, offering insights into bridging the gap between current functionalities and agent-level performance. To promote further research for LLMs to fully act as reliable agents in complex, real-world situations, we release our data and codes at https://github.com/tjunlp-lab/CToolEval.
%R 10.18653/v1/2024.findings-acl.928
%U https://aclanthology.org/2024.findings-acl.928/
%U https://doi.org/10.18653/v1/2024.findings-acl.928
%P 15711-15724
Markdown (Informal)
[CToolEval: A Chinese Benchmark for LLM-Powered Agent Evaluation in Real-World API Interactions](https://aclanthology.org/2024.findings-acl.928/) (Guo et al., Findings 2024)
ACL