@inproceedings{liu-etal-2024-beyond-text,
title = "Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with {M}ulti{API} Benchmark",
author = "Liu, Xiao and
Lin, Jianfeng and
Zhang, Jiawei",
editor = "Li, Sha and
Li, Manling and
Zhang, Michael JQ and
Choi, Eunsol and
Geva, Mor and
Hase, Peter and
Ji, Heng",
booktitle = "Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.knowllm-1.4",
doi = "10.18653/v1/2024.knowllm-1.4",
pages = "32--44",
abstract = "The proliferation of Large Language Models like ChatGPT has significantly advanced language understanding and generation, impacting a broad spectrum of applications. However, these models predominantly excel in text-based tasks, overlooking the complexity of real-world multimodal information. This study introduces \textbf{MultiAPI}, a pioneering comprehensive large-scale API benchmark dataset aimed at expanding LLMs{'} proficiency in multimodal contexts. Developed collaboratively through ChatGPT, \textbf{MultiAPI} consists of 187 diverse API calls and 1,799 contextual prompts, offering a unique platform evaluation of tool-augmented LLMs handling multimodal tasks. Through comprehensive experiments, our findings reveal that while LLMs demonstrate proficiency in API call decision-making, they face challenges in domain identification, function selection, and argument generation. What{'}s more, we surprisingly notice that auxiliary context can actually impair the performance. An in-depth error analysis paves the way for a new paradigm to address these challenges, suggesting a potential direction for future LLM research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-beyond-text">
<titleInfo>
<title>Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Zhang</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 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sha</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">JQ</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mor</namePart>
<namePart type="family">Geva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Hase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</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>The proliferation of Large Language Models like ChatGPT has significantly advanced language understanding and generation, impacting a broad spectrum of applications. However, these models predominantly excel in text-based tasks, overlooking the complexity of real-world multimodal information. This study introduces MultiAPI, a pioneering comprehensive large-scale API benchmark dataset aimed at expanding LLMs’ proficiency in multimodal contexts. Developed collaboratively through ChatGPT, MultiAPI consists of 187 diverse API calls and 1,799 contextual prompts, offering a unique platform evaluation of tool-augmented LLMs handling multimodal tasks. Through comprehensive experiments, our findings reveal that while LLMs demonstrate proficiency in API call decision-making, they face challenges in domain identification, function selection, and argument generation. What’s more, we surprisingly notice that auxiliary context can actually impair the performance. An in-depth error analysis paves the way for a new paradigm to address these challenges, suggesting a potential direction for future LLM research.</abstract>
<identifier type="citekey">liu-etal-2024-beyond-text</identifier>
<identifier type="doi">10.18653/v1/2024.knowllm-1.4</identifier>
<location>
<url>https://aclanthology.org/2024.knowllm-1.4</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>32</start>
<end>44</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark
%A Liu, Xiao
%A Lin, Jianfeng
%A Zhang, Jiawei
%Y Li, Sha
%Y Li, Manling
%Y Zhang, Michael JQ
%Y Choi, Eunsol
%Y Geva, Mor
%Y Hase, Peter
%Y Ji, Heng
%S Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F liu-etal-2024-beyond-text
%X The proliferation of Large Language Models like ChatGPT has significantly advanced language understanding and generation, impacting a broad spectrum of applications. However, these models predominantly excel in text-based tasks, overlooking the complexity of real-world multimodal information. This study introduces MultiAPI, a pioneering comprehensive large-scale API benchmark dataset aimed at expanding LLMs’ proficiency in multimodal contexts. Developed collaboratively through ChatGPT, MultiAPI consists of 187 diverse API calls and 1,799 contextual prompts, offering a unique platform evaluation of tool-augmented LLMs handling multimodal tasks. Through comprehensive experiments, our findings reveal that while LLMs demonstrate proficiency in API call decision-making, they face challenges in domain identification, function selection, and argument generation. What’s more, we surprisingly notice that auxiliary context can actually impair the performance. An in-depth error analysis paves the way for a new paradigm to address these challenges, suggesting a potential direction for future LLM research.
%R 10.18653/v1/2024.knowllm-1.4
%U https://aclanthology.org/2024.knowllm-1.4
%U https://doi.org/10.18653/v1/2024.knowllm-1.4
%P 32-44
Markdown (Informal)
[Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark](https://aclanthology.org/2024.knowllm-1.4) (Liu et al., KnowLLM-WS 2024)
ACL