大模型
arxiv.org ·
轻量级 AI 素养干预有助于抵御 AI 政治说服
arXiv 预印本（cs.HC）研究轻量级 AI 素养干预能否抵御 LLM 的政治说服。两项实验共 3,208 名美国参与者与被告知要改变其政治观点的 LLM 对话，结果显示加入简短警告后信念改变减少约一半（-48.1%，95% CI [-59.5%, -36.8%]），且未显著降低对生成式 AI 的整体信任。作者认为轻量素养干预可帮助用户抵御 AI 政治说服。
AI推荐理由 arXiv 预印本，作者为 Reed Orchinik 与 David Rand，摘要给出两项实验（合计 N=3,208 名美国人）的具体效应量：警告使信念改变减少约一半（-48.1%，95% CI [-59.5%, -36.8%]），且未显著降低对生成式 AI 的整体信任。这是关于 AI 说服风险与轻量干预的可验证实证结果，对 AI 安全、对齐与产品设计有参考价值。局限在于仅为预印本、尚未经同行评审，样本限定为美国政治话题，摘要未说明干预的长期效果与跨场景泛化性。
72
正文
Computer Science > Human-Computer Interaction
arXiv:2609.16432 (cs)
[Submitted on 14 Sep 2026 (v1), last revised 17 Sep 2026 (this version, v2)]
Title:A light-touch AI literacy intervention helps protect against AI political persuasion
Authors:Reed Orchinik, David Rand
View a PDF of the paper titled A light-touch AI literacy intervention helps protect against AI political persuasion, by Reed Orchinik and 1 other authors
View PDF
HTML (experimental)
Abstract:Conversations with large language models (LLMs) can substantially shift beliefs and attitudes, raising concerns about manipulation using AI persuasion. Here we test whether a light-touch AI literacy intervention - a brief warning that LLMs can be prompted to persuade and may present information selectively - helps protect users. Across two experiments (total N = 3,208 Americans) in which participants conversed with an LLM instructed to shift their views about different political topics, the presence of a warning reduced belief change by roughly one-half (-48.1%, 95% CI [-59.5%, -36.8%]) relative to the control. Importantly, the warning did not significantly reduce trust in generative AI more broadly. Light-touch literacy interventions can help protect users against AI political persuasion.
Subjects:
Human-Computer Interaction (cs.HC)
Cite as:
arXiv:2609.16432 [cs.HC]
(or
arXiv:2609.16432v2 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2609.16432
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Reed Orchinik [view email]
[v1]
Mon, 14 Sep 2026 23:18:33 UTC (277 KB)
[v2]
Thu, 17 Sep 2026 13:16:41 UTC (277 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled A light-touch AI literacy intervention helps protect against AI political persuasion, by Reed Orchinik and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.HC
new
|
recent
| 2026-09
Change to browse by:
cs
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?)