@inproceedings{chen-etal-2024-large,
title = "Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?",
author = "Chen, Yuyan and
Li, Yueze and
Yan, Songzhou and
Liu, Sijia and
Liang, Jiaqing and
Xiao, Yanghua",
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.131",
doi = "10.18653/v1/2024.findings-acl.131",
pages = "2225--2238",
abstract = "The evaluation of the problem-solving capability under incomplete information scenarios of Large Language Models (LLMs) is increasingly important, encompassing capabilities such as questioning, knowledge search, error detection, and path planning. Current research mainly focus on LLMs{'} problem-solving capability such as {``}Twenty Questions{''}.However, these kinds of games do not require recognizing misleading cues which are necessary in the incomplete information scenario.Moreover, the existing game such as {``}Who is undercover{''} are highly subjective, making it challenging for evaluation.Therefore, in this paper, we introduce a novel game named BrainKing based on the {``}Who is undercover{''} and {``}Twenty Questions{''} for evaluating LLM capabilities under incomplete information scenarios. It requires LLMs to identify target entities with limited yes-or-no questions and potential misleading answers. By setting up easy, medium, and hard difficulty modes, we comprehensively assess the performance of LLMs across various aspects. Our results reveal the capabilities and limitations of LLMs in BrainKing, providing significant insights of LLM problem-solving levels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-large">
<titleInfo>
<title>Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuyan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueze</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songzhou</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sijia</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqing</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</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>The evaluation of the problem-solving capability under incomplete information scenarios of Large Language Models (LLMs) is increasingly important, encompassing capabilities such as questioning, knowledge search, error detection, and path planning. Current research mainly focus on LLMs’ problem-solving capability such as “Twenty Questions”.However, these kinds of games do not require recognizing misleading cues which are necessary in the incomplete information scenario.Moreover, the existing game such as “Who is undercover” are highly subjective, making it challenging for evaluation.Therefore, in this paper, we introduce a novel game named BrainKing based on the “Who is undercover” and “Twenty Questions” for evaluating LLM capabilities under incomplete information scenarios. It requires LLMs to identify target entities with limited yes-or-no questions and potential misleading answers. By setting up easy, medium, and hard difficulty modes, we comprehensively assess the performance of LLMs across various aspects. Our results reveal the capabilities and limitations of LLMs in BrainKing, providing significant insights of LLM problem-solving levels.</abstract>
<identifier type="citekey">chen-etal-2024-large</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.131</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.131</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2225</start>
<end>2238</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?
%A Chen, Yuyan
%A Li, Yueze
%A Yan, Songzhou
%A Liu, Sijia
%A Liang, Jiaqing
%A Xiao, Yanghua
%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 chen-etal-2024-large
%X The evaluation of the problem-solving capability under incomplete information scenarios of Large Language Models (LLMs) is increasingly important, encompassing capabilities such as questioning, knowledge search, error detection, and path planning. Current research mainly focus on LLMs’ problem-solving capability such as “Twenty Questions”.However, these kinds of games do not require recognizing misleading cues which are necessary in the incomplete information scenario.Moreover, the existing game such as “Who is undercover” are highly subjective, making it challenging for evaluation.Therefore, in this paper, we introduce a novel game named BrainKing based on the “Who is undercover” and “Twenty Questions” for evaluating LLM capabilities under incomplete information scenarios. It requires LLMs to identify target entities with limited yes-or-no questions and potential misleading answers. By setting up easy, medium, and hard difficulty modes, we comprehensively assess the performance of LLMs across various aspects. Our results reveal the capabilities and limitations of LLMs in BrainKing, providing significant insights of LLM problem-solving levels.
%R 10.18653/v1/2024.findings-acl.131
%U https://aclanthology.org/2024.findings-acl.131
%U https://doi.org/10.18653/v1/2024.findings-acl.131
%P 2225-2238
Markdown (Informal)
[Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?](https://aclanthology.org/2024.findings-acl.131) (Chen et al., Findings 2024)
ACL