面向LLM人格模拟的自适应访谈：基于证据的推理提升决策对齐
Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision Alignment
AI总结：
提出自适应访谈框架，通过结构化三阶段对话收集人格相关信息，并基于访谈记录评估LLM在道德困境场景中模拟个体决策的能力，发现基于后续追问的证据推理能显著提升预测准确性。
摘要：
准确模拟特定个体的决策对大型语言模型（LLM）仍然具有挑战性，部分原因在于人格信息通常以静态描述形式提供，缺乏个体层面决策模拟所需的价值观、经历和情境线索。我们提出一种自适应访谈框架，通过结构化的三阶段对话收集人格相关信息：核心问题、动态追问和综合人格总结。利用生成的访谈记录，我们评估LLM能否模拟参与者在道德困境场景中的决策。我们比较了三种对话情境——核心10个问题回答、完整访谈对话以及总结性人格表征。结果发现，自适应访谈并非作为统一的准确性增强器，而更像是一种选择性接地机制：约40%的完整访谈轨迹中融入了基于追问的证据，且这些基于追问的预测比仅基于核心问题的预测更准确（45.5% vs. 39.3%）。这些发现强调，仅靠更丰富的人格背景是不够的：只有当模型真正将其决策基于用户特定证据时，改进才会出现。
英文摘要：
Accurately simulating the decisions of a specific individual remains challenging for large language models (LLMs), partly because persona information is often provided as static descriptions that miss the values, experiences, and contextual cues needed for individual-level decision simulation. We propose an adaptive interview framework that gathers persona-relevant information through a structured three-stage dialogue: core questions, dynamic follow-ups, and a synthesized personality summary. Using the resulting interview transcripts, we evaluate whether LLMs can simulate participants' decisions in moral dilemma scenarios. We compare three conversational contexts -- Core-10 responses, the full interview dialogue, and a summarized persona representation. We find that adaptive interviewing functions less as a uniform accuracy booster and more as a selective grounding mechanism: follow-up-derived evidence is incorporated in around 40% of full-interview traces, and these follow-up-grounded predictions are more accurate than core-only grounded ones (45.5% vs. 39.3%). These findings highlight that richer persona context alone is insufficient: improvements arise only when models actually ground their decisions in user-specific evidence.
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。
