@inproceedings{yu-etal-2026-probing,
title = "Probing Fine-Grained Stereotypes and Trait Structure in Large Language Models",
author = "Yu, Rebecca and
Deas, Nicholas and
Leach, Colin Wayne and
McKeown, Kathleen",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2370/",
pages = "50919--50947",
ISBN = "979-8-89176-462-0",
abstract = "We study fine-grained stereotypes of LLMs activated by linguistic features representing demographic groups, developing a probe-based framework to extract 235 fine-grained traits (e.g., friendly, uneducated, honest) from model representations of prompts. Using these probes, we conduct two studies analyzing the underlying structure of traits and specific stereotypes of demographic groups. We find that fine-grained trait information is represented in LLMs similarly to coarse stereotype content dimensions (e.g., warmth and competence), and that the latent factors of trait probes (e.g., morality, competence, sociability) largely align with those in the psychology literature (Fiske et al., 2002) despite traits being modeled independently. Finally, we extract LLMs' associations between traits and demographics signaled through language to surface granular stereotypes encoded in LLMs. We, for example, find that the evaluated models encode associations between African American Language and traits clumsy, uneducated, and criminal. These associations may reinforce harmful stereotypes, with implications for both general dialogue responses and in domains like hiring. Overall, we discuss the need to consider fine-grained traits in stereotype evaluations in order to distinguish stereotypes of out-groups and between models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2026-probing">
<titleInfo>
<title>Probing Fine-Grained Stereotypes and Trait Structure in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Deas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="given">Wayne</namePart>
<namePart type="family">Leach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>We study fine-grained stereotypes of LLMs activated by linguistic features representing demographic groups, developing a probe-based framework to extract 235 fine-grained traits (e.g., friendly, uneducated, honest) from model representations of prompts. Using these probes, we conduct two studies analyzing the underlying structure of traits and specific stereotypes of demographic groups. We find that fine-grained trait information is represented in LLMs similarly to coarse stereotype content dimensions (e.g., warmth and competence), and that the latent factors of trait probes (e.g., morality, competence, sociability) largely align with those in the psychology literature (Fiske et al., 2002) despite traits being modeled independently. Finally, we extract LLMs’ associations between traits and demographics signaled through language to surface granular stereotypes encoded in LLMs. We, for example, find that the evaluated models encode associations between African American Language and traits clumsy, uneducated, and criminal. These associations may reinforce harmful stereotypes, with implications for both general dialogue responses and in domains like hiring. Overall, we discuss the need to consider fine-grained traits in stereotype evaluations in order to distinguish stereotypes of out-groups and between models.</abstract>
<identifier type="citekey">yu-etal-2026-probing</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2370/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>50919</start>
<end>50947</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probing Fine-Grained Stereotypes and Trait Structure in Large Language Models
%A Yu, Rebecca
%A Deas, Nicholas
%A Leach, Colin Wayne
%A McKeown, Kathleen
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F yu-etal-2026-probing
%X We study fine-grained stereotypes of LLMs activated by linguistic features representing demographic groups, developing a probe-based framework to extract 235 fine-grained traits (e.g., friendly, uneducated, honest) from model representations of prompts. Using these probes, we conduct two studies analyzing the underlying structure of traits and specific stereotypes of demographic groups. We find that fine-grained trait information is represented in LLMs similarly to coarse stereotype content dimensions (e.g., warmth and competence), and that the latent factors of trait probes (e.g., morality, competence, sociability) largely align with those in the psychology literature (Fiske et al., 2002) despite traits being modeled independently. Finally, we extract LLMs’ associations between traits and demographics signaled through language to surface granular stereotypes encoded in LLMs. We, for example, find that the evaluated models encode associations between African American Language and traits clumsy, uneducated, and criminal. These associations may reinforce harmful stereotypes, with implications for both general dialogue responses and in domains like hiring. Overall, we discuss the need to consider fine-grained traits in stereotype evaluations in order to distinguish stereotypes of out-groups and between models.
%U https://aclanthology.org/2026.findings-emnlp.2370/
%P 50919-50947
Markdown (Informal)
[Probing Fine-Grained Stereotypes and Trait Structure in Large Language Models](https://aclanthology.org/2026.findings-emnlp.2370/) (Yu et al., Findings 2026)
ACL