大模型
arxiv.org ·
LLM 决策中的表层信念
论文研究 LLM 在二选一任务中是仅模仿理由，还是选择反映系统性决策结构。作者用合成二元决策设定，让模型在由分级属性定义的选项间选择，并比较模型自称最重要的属性与行为模型拟合出的实际驱动属性。行为模型对留出选择预测良好，说明行为与可见属性系统性相关；但模型自述和独立评分判断只能部分还原行为推断的驱动因素。该模式在提示顺序、采样扰动、替代行为模型、定向遮挡和不同决策结构下均成立。作者据此提出“表层信念”：模型行为上像受属性上的概率性局部优先级引导，但对其决策驱动因素的语言访问有限。
AI推荐理由 arXiv 论文（cs.AI），作者为 Gabriel Freedman 与 Francesca Toni，摘要明确给出方法与结论：在合成二元决策任务中，用行为模型拟合先前选择可较好预测留出选择，说明模型行为与可见属性系统性相关而非随机；但模型自述理由与独立评分判断只能部分还原行为推断出的驱动属性。该结论在提示顺序、采样扰动、替代行为模型、定向遮挡分析和不同决策结构下保持稳定，作者据此提出 LLM 决策中的“表层信念”概念。局限在于实验基于合成二元决策设定，摘要未给出具体模型清单、样本规模与效应量，结论外推需谨慎。
72
正文
Computer Science > Artificial Intelligence
arXiv:2606.11016 (cs)
[Submitted on 9 Jun 2026 (v1), last revised 15 Sep 2026 (this version, v2)]
Title:Superficial Beliefs in LLM Decision-Making
Authors:Gabriel Freedman, Francesca Toni
View a PDF of the paper titled Superficial Beliefs in LLM Decision-Making, by Gabriel Freedman and Francesca Toni
View PDF
HTML (experimental)
Abstract:We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure. Using synthetic binary decision settings in which models choose between profiles defined by graded attributes, we compare the attribute a model says mattered most with the attribute that best explains its choice under a behavioural model fit to prior decisions. The behavioural model predicts held-out choices well, showing that model behaviour is systematically related to the visible attributes rather than being random. However, direct self-reports and a separate score-based judge recover the behaviourally inferred driver only partially. The resulting picture is neither one of arbitrary behaviour nor one of fully articulated belief - outputs are structured enough to support prediction, but explicit reasons track the recovered driver only imperfectly. This qualitative pattern persists across prompt-order and sampling perturbations, alternative behavioural models, targeted occlusion analyses, and structurally varied decision settings. We interpret this as evidence for ``superficial belief'' in LLM decision-making: models behave as if guided by probabilistic local priorities over attributes, while having only limited verbal access to the attributes that drive their decisions.
Comments:
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2606.11016 [cs.AI]
(or
arXiv:2606.11016v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.11016
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Gabriel Freedman [view email]
[v1]
Tue, 9 Jun 2026 15:54:35 UTC (516 KB)
[v2]
Tue, 15 Sep 2026 14:18:12 UTC (517 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Superficial Beliefs in LLM Decision-Making, by Gabriel Freedman and Francesca Toni
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-06
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?)