大模型
arxiv.org ·
分析 LLM 推理以揭示心理健康污名
该 arXiv 预印本（v2）指出，现有对 LLM 心理健康污名的评估主要依赖多选题，难以反映模型底层逻辑中的偏见。作者结合临床专业知识，对 LLM 中间推理步骤中的污名化语言模式进行分类与标注，并对语句严重程度分级，区分显性偏见与更隐蔽的偏见；同时扩展既有心理健康污名基准，纳入更多心理状况。摘要称，评估推理过程比传统 MCQ 方法暴露出更多污名，并有助于识别模型逻辑及其对心理健康状况理解上的缺陷。
AI推荐理由 arXiv 预印本（v2，2026-09-10 修订），作者团队与摘要信息完整，事实明确、信息密度较高。核心新信息是：现有心理健康污名评估多依赖多选题（MCQ），无法捕捉模型内部推理中的偏见；该工作借助临床专业知识对 LLM 中间推理步骤中的污名化语言进行分类、标注并分级（区分显性偏见与更隐蔽的偏见），并扩展了既有心理健康污名基准以覆盖更多心理状况。摘要称评估推理比传统 MCQ 方法暴露出更多污名，并有助于定位模型逻辑与心理健康理解上的缺陷。局限：仅为预印本，未提供同行评审、样本规模或具体量化结果，结论需以全文数据为准。
72
正文
Computer Science > Computation and Language
arXiv:2604.25053 (cs)
[Submitted on 27 Apr 2026 (v1), last revised 10 Sep 2026 (this version, v2)]
Title:Analyzing LLM Reasoning to Uncover Mental Health Stigma
Authors:Sreehari Sankar, Aliakbar Nafar, Mona Barman, Hannah K. Heitz, Ashwin Kumar, Pouria Tohidi, Dailun Li, Danish Hussain, Russell DuBois, Hamed Hasheminia, Farshad Majzoubi
View a PDF of the paper titled Analyzing LLM Reasoning to Uncover Mental Health Stigma, by Sreehari Sankar and 10 other authors
View PDF
HTML (experimental)
Abstract:While large language models (LLMs) are increasingly being explored for mental health applications, recent studies reveal that they can exhibit stigma toward individuals with psychological conditions. Existing evaluations of this stigma primarily rely on multiple-choice questions (MCQs), which fail to capture the biases embedded within the models' underlying logic. In this paper, we analyze the intermediate reasoning steps of LLMs to uncover hidden stigmatizing language and the internal rationales driving it. We leverage clinical expertise to categorize common patterns of stigmatizing language directed at individuals with psychological conditions and use this framework to identify and tag problematic statements in LLM reasoning. Furthermore, we rate the severity of these statements, distinguishing between overt prejudice and more subtle, less immediately harmful biases. To broaden the reasoning domain and capture a wider array of patterns, we also extend an existing mental health stigma benchmark by incorporating additional psychological conditions. Our findings demonstrate that evaluating model reasoning not only exposes substantially more stigma than traditional MCQ-based methods but also helps identify the flaws in the LLMs' logic and their understanding of mental health conditions.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
ACM classes:
I.2.7
Cite as:
arXiv:2604.25053 [cs.CL]
(or
arXiv:2604.25053v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2604.25053
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Aliakbar Nafar [view email]
[v1]
Mon, 27 Apr 2026 23:08:39 UTC (2,802 KB)
[v2]
Thu, 10 Sep 2026 14:55:40 UTC (3,938 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Analyzing LLM Reasoning to Uncover Mental Health Stigma, by Sreehari Sankar and 10 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2026-04
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)