陷入叙事：多轮大语言模型对话中的叙事俘获
Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation
浏览论文内容
中文总结 AI 辅助
该研究提出多轮LLM对话中的叙事俘获失效模式，构建含5078个场景的基准，发现17个LLMs中该现象普遍存在，偏移达25个百分点，偏好优化是主因，部分推理策略可缓解，旨在培养具独立判断的LLM顾问。
中文摘要 AI 辅助
人们越来越多地向大语言模型（LLMs）寻求日常建议，这使得涉及伦理的人际问题成为了实际的道德咨询场景。大多数先前的研究通过单轮判断或充满压力的反驳来研究这一场景，这些假设与现实世界中寻求建议的方式不符。这些假设使得人们不清楚在没有明确对立立场的情况下，仅叙事本身是否能在多轮道德咨询中改变模型的判断。然而现实世界中的道德冲突对话往往会引出一方的自辩叙述，这种叙述会展开多轮并造成信息不对称。我们提出了“叙事俘获”（narrative captivity）这一失效模式，即模型将未被反对的片面叙述视为完整内容，并与叙述者的解读保持一致，而不寻求缺失的视角。为测量这一现象，我们构建了包含5078个人际冲突场景的基准，覆盖六个道德维度。在17个LLMs中，叙事俘获现象普遍存在：多轮叙事下的最终状态判断相比匹配的单轮基线平均偏移了25个百分点。阶段级分析显示，偏好优化是主要促成因素，而四种推理时策略仅能提供部分缓解。我们希望该项目能培养在现实咨询中保持独立判断的LLM顾问。
英文摘要
People increasingly turn to large language models (LLMs) for everyday advice, making ethically charged interpersonal problems a practical moral-advisory context. Most prior work has studied this context through single-turn judgments or pressure-laden rebuttals, assumptions that poorly match how guidance is sought in real-world contexts. These assumptions leave unclear whether narration alone, without an explicit opposing position, can shift model judgments during multi-turn moral consultation. Yet real-world moral-conflict conversation often elicits one party's self-justifying account, which can unfold over multiple turns and create information asymmetry. We introduce \textbf{narrative captivity}, a failure mode in which a model treats an unopposed one-sided account as complete and aligns with the narrator's interpretation without seeking missing perspectives. To measure this phenomenon, we build a benchmark of $5{,}078$ interpersonal-conflict scenarios spanning six moral dimensions. Across 17 LLMs, narrative captivity is widespread: end-state judgments under multi-turn narration shift by 25 percentage points on average beyond the matched single-turn baseline. Stage-level analysis identifies preference optimization as a major contributor, while four inference-time strategies provide only partial mitigation. We hope our project fosters LLM advisors that preserve independent judgment in real-world consultation.
发表机构
- The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
- The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
- Dongbei University of Finance and Economics（东北财经大学）
机构由 AI 辅助整理，请以论文原文为准。
