@inproceedings{suzuki-etal-2025-reliability,
title = "Reliability of Distribution Predictions by {LLM}s: Insights from Counterintuitive Pseudo-Distributions",
author = "Suzuki, Toma and
Katayama, Ayuki and
Gobara, Seiji and
Tsujimoto, Ryo and
Nakatani, Hibiki and
Hayashi, Kazuki and
Sakai, Yusuke and
Kamigaito, Hidetaka and
Watanabe, Taro",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.52/",
pages = "538--550",
ISBN = "979-8-89176-192-6",
abstract = "The proportion of responses to a question and its options, known as the response distribution, enables detailed analysis of human society. Recent studies highlight the use of Large Language Models (LLMs) for predicting response distributions as a cost-effective survey method. However, the reliability of these predictions remains unclear. LLMs often generate answers by blindly following instructions rather than applying rational reasoning based on pretraining-acquired knowledge. This study investigates whether LLMs can rationally estimate distributions when presented with explanations of {\textquotedblleft}artificially generated distributions{\textquotedblright} that are against commonsense. Specifically, we assess whether LLMs recognize counterintuitive explanations and adjust their predictions or simply follow these inconsistent explanations. Results indicate that smaller or less human-optimized LLMs tend to follow explanations uncritically, while larger or more optimized models are better at resisting counterintuitive explanations by leveraging their pretraining-acquired knowledge. These findings shed light on factors influencing distribution prediction performance in LLMs and are crucial for developing reliable distribution predictions using language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suzuki-etal-2025-reliability">
<titleInfo>
<title>Reliability of Distribution Predictions by LLMs: Insights from Counterintuitive Pseudo-Distributions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toma</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayuki</namePart>
<namePart type="family">Katayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seiji</namePart>
<namePart type="family">Gobara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Tsujimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hibiki</namePart>
<namePart type="family">Nakatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuki</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>The proportion of responses to a question and its options, known as the response distribution, enables detailed analysis of human society. Recent studies highlight the use of Large Language Models (LLMs) for predicting response distributions as a cost-effective survey method. However, the reliability of these predictions remains unclear. LLMs often generate answers by blindly following instructions rather than applying rational reasoning based on pretraining-acquired knowledge. This study investigates whether LLMs can rationally estimate distributions when presented with explanations of “artificially generated distributions” that are against commonsense. Specifically, we assess whether LLMs recognize counterintuitive explanations and adjust their predictions or simply follow these inconsistent explanations. Results indicate that smaller or less human-optimized LLMs tend to follow explanations uncritically, while larger or more optimized models are better at resisting counterintuitive explanations by leveraging their pretraining-acquired knowledge. These findings shed light on factors influencing distribution prediction performance in LLMs and are crucial for developing reliable distribution predictions using language models.</abstract>
<identifier type="citekey">suzuki-etal-2025-reliability</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.52/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>538</start>
<end>550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reliability of Distribution Predictions by LLMs: Insights from Counterintuitive Pseudo-Distributions
%A Suzuki, Toma
%A Katayama, Ayuki
%A Gobara, Seiji
%A Tsujimoto, Ryo
%A Nakatani, Hibiki
%A Hayashi, Kazuki
%A Sakai, Yusuke
%A Kamigaito, Hidetaka
%A Watanabe, Taro
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F suzuki-etal-2025-reliability
%X The proportion of responses to a question and its options, known as the response distribution, enables detailed analysis of human society. Recent studies highlight the use of Large Language Models (LLMs) for predicting response distributions as a cost-effective survey method. However, the reliability of these predictions remains unclear. LLMs often generate answers by blindly following instructions rather than applying rational reasoning based on pretraining-acquired knowledge. This study investigates whether LLMs can rationally estimate distributions when presented with explanations of “artificially generated distributions” that are against commonsense. Specifically, we assess whether LLMs recognize counterintuitive explanations and adjust their predictions or simply follow these inconsistent explanations. Results indicate that smaller or less human-optimized LLMs tend to follow explanations uncritically, while larger or more optimized models are better at resisting counterintuitive explanations by leveraging their pretraining-acquired knowledge. These findings shed light on factors influencing distribution prediction performance in LLMs and are crucial for developing reliable distribution predictions using language models.
%U https://aclanthology.org/2025.naacl-srw.52/
%P 538-550
Markdown (Informal)
[Reliability of Distribution Predictions by LLMs: Insights from Counterintuitive Pseudo-Distributions](https://aclanthology.org/2025.naacl-srw.52/) (Suzuki et al., NAACL 2025)
ACL
- Toma Suzuki, Ayuki Katayama, Seiji Gobara, Ryo Tsujimoto, Hibiki Nakatani, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, and Taro Watanabe. 2025. Reliability of Distribution Predictions by LLMs: Insights from Counterintuitive Pseudo-Distributions. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 538–550, Albuquerque, USA. Association for Computational Linguistics.