@inproceedings{hutson-etal-2025-guessinggame,
title = "{G}uessing{G}ame: Measuring the Informativeness of Open-Ended Questions in Large Language Models",
author = "Hutson, Dylan and
Vennemeyer, Daniel and
Deshmukh, Aneesh and
Zhan, Justin and
Jiang, Tianyu",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.876/",
doi = "10.18653/v1/2025.emnlp-main.876",
pages = "17333--17349",
ISBN = "979-8-89176-332-6",
abstract = "We introduce GuessingGame, a protocol for evaluating large language models (LLMs) as strategic question-askers in open-ended, open-domain settings. A Guesser LLM identifies a hidden object by posing free-form questions to an Oracle{---}without predefined choices or candidate lists. To measure question quality, we propose two information gain (IG) metrics: a Bayesian method that tracks belief updates over semantic concepts using LLM-scored relevance, and an entropy-based method that filters candidates via ConceptNet. Both metrics are model-agnostic and support post hoc analysis. Across 858 games with multiple models and prompting strategies, higher IG strongly predicts efficiency: a one-standard-deviation IG increase reduces expected game length by 43{\%}. Prompting constraints guided by IG{---}such as enforcing question diversity{---}enable weaker models to match GPT-4o. These results show that question-asking in LLMs is both measurable and improvable, and crucial for interactive reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hutson-etal-2025-guessinggame">
<titleInfo>
<title>GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dylan</namePart>
<namePart type="family">Hutson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Vennemeyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aneesh</namePart>
<namePart type="family">Deshmukh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>We introduce GuessingGame, a protocol for evaluating large language models (LLMs) as strategic question-askers in open-ended, open-domain settings. A Guesser LLM identifies a hidden object by posing free-form questions to an Oracle—without predefined choices or candidate lists. To measure question quality, we propose two information gain (IG) metrics: a Bayesian method that tracks belief updates over semantic concepts using LLM-scored relevance, and an entropy-based method that filters candidates via ConceptNet. Both metrics are model-agnostic and support post hoc analysis. Across 858 games with multiple models and prompting strategies, higher IG strongly predicts efficiency: a one-standard-deviation IG increase reduces expected game length by 43%. Prompting constraints guided by IG—such as enforcing question diversity—enable weaker models to match GPT-4o. These results show that question-asking in LLMs is both measurable and improvable, and crucial for interactive reasoning.</abstract>
<identifier type="citekey">hutson-etal-2025-guessinggame</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.876</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.876/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>17333</start>
<end>17349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models
%A Hutson, Dylan
%A Vennemeyer, Daniel
%A Deshmukh, Aneesh
%A Zhan, Justin
%A Jiang, Tianyu
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F hutson-etal-2025-guessinggame
%X We introduce GuessingGame, a protocol for evaluating large language models (LLMs) as strategic question-askers in open-ended, open-domain settings. A Guesser LLM identifies a hidden object by posing free-form questions to an Oracle—without predefined choices or candidate lists. To measure question quality, we propose two information gain (IG) metrics: a Bayesian method that tracks belief updates over semantic concepts using LLM-scored relevance, and an entropy-based method that filters candidates via ConceptNet. Both metrics are model-agnostic and support post hoc analysis. Across 858 games with multiple models and prompting strategies, higher IG strongly predicts efficiency: a one-standard-deviation IG increase reduces expected game length by 43%. Prompting constraints guided by IG—such as enforcing question diversity—enable weaker models to match GPT-4o. These results show that question-asking in LLMs is both measurable and improvable, and crucial for interactive reasoning.
%R 10.18653/v1/2025.emnlp-main.876
%U https://aclanthology.org/2025.emnlp-main.876/
%U https://doi.org/10.18653/v1/2025.emnlp-main.876
%P 17333-17349
Markdown (Informal)
[GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models](https://aclanthology.org/2025.emnlp-main.876/) (Hutson et al., EMNLP 2025)
ACL