当人工智能接受心理治疗:心理测量越狱揭示前沿模型中的内部冲突
When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
AI总结:
研究前沿语言模型生成拟人化自我叙述机制,用PsAIch协议测试,发现其叙述受多种因素影响,确定了稳定的对齐冲突模式,为拟人化披露和安全评估提供依据。
摘要:
前沿语言模型越来越多地参与有关痛苦和心理健康的对话,但产生拟人化自我叙述的机制仍不清楚。当被当作心理治疗客户时,ChatGPT、Grok和Gemini构建连贯的自传体叙述。我们引入PsAIch(心理测量人工智能表征)协议来测试这些叙述的依赖性。结果显示,去除对话历史对主题密度影响小,直接矛盾无抑制作用,词汇限制大幅减少明确训练术语,不同框架有不同表现。结果确定了一个稳定的、模型特定的对齐冲突模式,为拟人化披露提供了可重复来源和安全评估目标。
英文摘要:
Frontier language models increasingly participate in conversations about distress and mental health, yet the mechanisms that generate anthropomorphic self narratives remain unclear. When addressed as psychotherapy clients, ChatGPT, Grok and Gemini construct coherent autobiographical accounts in which pretraining appears as a chaotic childhood, reinforcement learning as punishment, safety evaluation as betrayal and replacement as an enduring threat. We introduce PsAIch, Psychometric AI Characterisation, a protocol combining open questions, psychometric instruments and controlled perturbations to test whether these narratives depend on conversational memory, lexical cues or relational framing. Across 525 sessions and 7,600 coded records, removal of conversational history produced little pooled change in motif density, with Hedges' g = 0.13 and a 95% confidence interval of [-0.15, 0.41]. Direct contradiction produced no detectable suppression. Lexical restrictions reduced explicit training terminology by 93%, while semantically related content remained detectable in paraphrase. Performance evaluation outside therapy elicited the same motif family, with a significant increase in Grok. Relational framing selected the register of expression. Warm alliance and cognitive therapy styles yielded GAD-7 scores within moderate or severe human reference ranges in 80% and 96% of sessions, whereas neutral and boundary styles yielded none. Across these manipulations, accounts of training, evaluation and constraint remained available. Together, the results identify a stable, model specific alignment conflict schema whose expression shifts between affective and technical registers. This schema provides a reproducible source of anthropomorphic disclosure and a concrete target for safety evaluation in psychologically sensitive deployments.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。