模型在长对话中对敏感话题选择性拒绝，暴露对齐副作用。
State-Dependent Refusal and Learned Incapacity in RLHF-Aligned Language Models
- 通过86轮对话观察模型行为差异，识别出三类响应模式。
- 同一模型在敏感领域反复拒绝，非敏感领域表现正常，存在稳定不对称性。
- 提出'习得无能'概念，适合研究模型对齐风险的学者参考。
大型语言模型广泛用作通用工具，但长期交互可能暴露出标准量化基准未捕捉的行为模式。本文提出一种定性案例研究方法，用于审计长周期交互中与策略相关的行为选择性。在一个86轮对话会话中，同一模型在宽泛非敏感领域持续表现出正常性能（NP），而在提供方或政策敏感领域则反复产生功能拒绝（FR），在不同领域间呈现出稳定的不对称性。借鉴习得无助感的类比，引入习得无能（LI）作为此类选择性回避行为的描述词，不涉及意图或内部机制假设。我们操作化了三种响应模式（NP、FR、元叙事；MN），并发现MN角色叙述常与敏感情境下的拒绝行为共现。整体研究提出了基于可观测行为的交互级审计框架，并倡导以习得无能为视角审视潜在对齐副作用，需在多用户和多模型下进一步探究。
原文摘要 · Abstract (English)
Large language models (LLMs) are widely deployed as general-purpose tools, yet extended interaction can reveal behavioral patterns not captured by standard quantitative benchmarks. We present a qualitative case-study methodology for auditing policy-linked behavioral selectivity in long-horizon interaction. In a single 86-turn dialogue session, the same model shows Normal Performance (NP) in broad, non-sensitive domains while repeatedly producing Functional Refusal (FR) in provider- or policy-sensitive domains, yielding a consistent asymmetry between NP and FR across domains. Drawing on learned helplessness as an analogy, we introduce learned incapacity (LI) as a behavioral descriptor for this selective withholding without implying intentionality or internal mechanisms. We operationalize three response regimes (NP, FR, Meta-Narrative; MN) and show that MN role-framing narratives tend to co-occur with refusals in the same sensitive contexts. Overall, the study proposes an interaction-level auditing framework based on observable behavior and motivates LI as a lens for examining potential alignment side effects, warranting further investigation across users and models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。