人格错觉：揭示大语言模型中自我报告与行为之间的脱节
The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
AI总结：
该研究系统探究大语言模型的人格特征，发现指令对齐可稳定特质表达但自我报告的人格无法可靠预测行为，人格注入仅影响自我报告难改变实际行为，挑战了LLM人格相关假设，强调需深化对齐与可解释性评估。
摘要：
长期以来，人格特质一直被视作人类行为的预测指标开展研究。大语言模型（LLM）的最新进展表明，人工系统中可能出现类似模式——先进的LLM展现出稳定的行为倾向，与人类的宜人性、自我调节等特质相似。理解这些模式至关重要，但既往研究主要依赖简化的自我报告和启发式提示，几乎未开展行为层面的验证。本研究从三个维度系统刻画LLM的人格特征：（1）训练各阶段特质轮廓的动态涌现与演化；（2）自我报告特质在行为任务中的预测效度；（3）人格注入等定向干预对自我报告和行为的影响。研究结果显示，指令对齐（如RLHF、指令微调）显著稳定了特质表达，并以与人类数据相似的方式强化了特质间的相关性。然而，这些自我报告的特质无法可靠预测行为，且观察到的关联模式常与人类模式存在差异。尽管人格注入成功地将自我报告导向预期方向，但它对实际行为的影响微弱或不一致。通过区分表层特质表达与行为一致性，本研究结果挑战了关于LLM人格的假设，凸显了在对齐与可解释性领域开展更深度评估的必要性。
英文摘要：
Personality traits have long been studied as predictors of human behavior. Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems, with advanced LLMs displaying consistent behavioral tendencies resembling human traits like agreeableness and self-regulation. Understanding these patterns is crucial, yet prior work primarily relied on simplified self-reports and heuristic prompting, with little behavioral validation. In this study, we systematically characterize LLM personality across three dimensions: (1) the dynamic emergence and evolution of trait profiles throughout training stages; (2) the predictive validity of self-reported traits in behavioral tasks; and (3) the impact of targeted interventions, such as persona injection, on both self-reports and behavior. Our findings reveal that instructional alignment (e.g., RLHF, instruction tuning) significantly stabilizes trait expression and strengthens trait correlations in ways that mirror human data. However, these self-reported traits do not reliably predict behavior, and observed associations often diverge from human patterns. While persona injection successfully steers self-reports in the intended direction, it exerts little or inconsistent effect on actual behavior. By distinguishing surface-level trait expression from behavioral consistency, our findings challenge assumptions about LLM personality and underscore the need for deeper evaluation in alignment and interpretability.
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。
