@inproceedings{qian-etal-2025-mask,
title = "To Mask or to Mirror: Human-{AI} Alignment in Collective Reasoning",
author = {Qian, Crystal and
Parisi, Aaron T and
Bouleau, Cl{\'e}mentine and
Tsai, Vivian and
Lebreton, Ma{\"e}l and
Dixon, Lucas},
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.122/",
doi = "10.18653/v1/2025.emnlp-main.122",
pages = "2398--2423",
ISBN = "979-8-89176-332-6",
abstract = "As large language models (LLMs) are increasingly used to model and augment collective decision-making, it is critical to examine their alignment with human social reasoning. We present an empirical framework for assessing collective alignment, in contrast to prior work on the individual level. Using the Lost at Sea social psychology task, we conduct a large-scale online experiment (N=748), randomly assigning groups to leader elections with either visible demographic attributes (e.g. name, gender) or pseudonymous aliases. We then simulate matched LLM groups conditioned on the human data, benchmarking Gemini 2.5, GPT-4.1, Claude Haiku 3.5, and Gemma 3. LLM behaviors diverge: some mirror human biases; others mask these biases and attempt to compensate for them. We empirically demonstrate that human-AI alignment in collective reasoning depends on context, cues, and model-specific inductive biases. Understanding how LLMs align with collective human behavior is critical to advancing socially-aligned AI, and demands dynamic benchmarks that capture the complexities of collective reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-etal-2025-mask">
<titleInfo>
<title>To Mask or to Mirror: Human-AI Alignment in Collective Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Crystal</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Parisi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clémentine</namePart>
<namePart type="family">Bouleau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maël</namePart>
<namePart type="family">Lebreton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Dixon</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>As large language models (LLMs) are increasingly used to model and augment collective decision-making, it is critical to examine their alignment with human social reasoning. We present an empirical framework for assessing collective alignment, in contrast to prior work on the individual level. Using the Lost at Sea social psychology task, we conduct a large-scale online experiment (N=748), randomly assigning groups to leader elections with either visible demographic attributes (e.g. name, gender) or pseudonymous aliases. We then simulate matched LLM groups conditioned on the human data, benchmarking Gemini 2.5, GPT-4.1, Claude Haiku 3.5, and Gemma 3. LLM behaviors diverge: some mirror human biases; others mask these biases and attempt to compensate for them. We empirically demonstrate that human-AI alignment in collective reasoning depends on context, cues, and model-specific inductive biases. Understanding how LLMs align with collective human behavior is critical to advancing socially-aligned AI, and demands dynamic benchmarks that capture the complexities of collective reasoning.</abstract>
<identifier type="citekey">qian-etal-2025-mask</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.122</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.122/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2398</start>
<end>2423</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Mask or to Mirror: Human-AI Alignment in Collective Reasoning
%A Qian, Crystal
%A Parisi, Aaron T.
%A Bouleau, Clémentine
%A Tsai, Vivian
%A Lebreton, Maël
%A Dixon, Lucas
%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 qian-etal-2025-mask
%X As large language models (LLMs) are increasingly used to model and augment collective decision-making, it is critical to examine their alignment with human social reasoning. We present an empirical framework for assessing collective alignment, in contrast to prior work on the individual level. Using the Lost at Sea social psychology task, we conduct a large-scale online experiment (N=748), randomly assigning groups to leader elections with either visible demographic attributes (e.g. name, gender) or pseudonymous aliases. We then simulate matched LLM groups conditioned on the human data, benchmarking Gemini 2.5, GPT-4.1, Claude Haiku 3.5, and Gemma 3. LLM behaviors diverge: some mirror human biases; others mask these biases and attempt to compensate for them. We empirically demonstrate that human-AI alignment in collective reasoning depends on context, cues, and model-specific inductive biases. Understanding how LLMs align with collective human behavior is critical to advancing socially-aligned AI, and demands dynamic benchmarks that capture the complexities of collective reasoning.
%R 10.18653/v1/2025.emnlp-main.122
%U https://aclanthology.org/2025.emnlp-main.122/
%U https://doi.org/10.18653/v1/2025.emnlp-main.122
%P 2398-2423
Markdown (Informal)
[To Mask or to Mirror: Human-AI Alignment in Collective Reasoning](https://aclanthology.org/2025.emnlp-main.122/) (Qian et al., EMNLP 2025)
ACL
- Crystal Qian, Aaron T Parisi, Clémentine Bouleau, Vivian Tsai, Maël Lebreton, and Lucas Dixon. 2025. To Mask or to Mirror: Human-AI Alignment in Collective Reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 2398–2423, Suzhou, China. Association for Computational Linguistics.