arXiv cs.AI· Oliver Lack, Lana Tikhomirov, Humphrey Thompson, Carolyn Semmler, Melissa McCradden·· 2 小时前AI 评分36
思维链如何催生拟人化、认知优越感与对 AI 的盲从：当推理表象被误读为隐藏的理解
When Reasoning looks like Hidden Understanding: How Chain-of-Thought Fosters Anthropomorphism, Perceptions of Epistemic Superiority, and Cognitive Deference
AI 导读
一篇 arXiv 论文指出，用户常把生成式模型的语言形式误读为“理解”，而模型只是复现语言模式；思维链（CoT）“解释推理”进一步强化了拟人化、认知权威感与对 AI 的认知服从。作者以医学为例，论证通过 CoT 实现的可解释性存在严重问题，反而削弱其想服务的伦理原则。论文建议不再鼓励让模型输出面向用户的理由，并在 AI 素养培训中明确警示。
正文 · 原文
Abstract:As AI-based products permeate society, specifically systems using generative models, a belief system is emerging about what these products are and what they can and cannot do. One common belief concerns the perception of the form of language as evidence of 'understanding' language. As these generative models reproduce linguistic patterns rather than understand meaning, interpreting these patterns as evidence of understanding is a misattribution. This misconception is extended by the notion that generative models can 'explain their reasoning.' Anecdotally, these misconceptions which mistake the form of language for its meaning are driving cognitive deference to AI systems in a way that displaces human agency. Such mistakes involve attributions of cognitive properties to the system, allowing them to be treated like intentional 'minds'. Importantly, perceived epistemic authority and superiority make that 'mind' worth deferring to. Anthropomorphism in tandem with epistemic authority and superiority, we argue, increases the risk that users generalise from narrow task performance to broader competencies, committing the "fallacy of composition". This paper explores misconceptions of Chain of Thought (CoT) reasoning as sufficient transparent 'explanation'. We explore how anthropomorphism acts as a vehicle for cognitive deference of decision-making and perceptions of epistemic superiority in AI systems. Finally, we explore CoT's ramifications using medicine as an example. Taken together, we conclude that explainability operationalised through CoT is highly problematic and undercuts the very ethical principles it is intended to serve. While CoT may be valuable for improving output accuracy and moderation, we suggest that the practice of asking models to provide user facing reasons for their outputs should be actively discouraged, and AI literacy training should explicitly caution against its use.
| Comments: | Conference submission to FAccT, 4th November 2026. No Figures |
| Subjects: | Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2611.13456 [cs.AI] |
| (or arXiv:2611.13456v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13456 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Oliver Lack [view email]
[v1]
Tue, 10 Nov 2026 02:00:52 UTC (100 KB)
来源：arXiv cs.AI · arxiv.org