用不确定性策略提升AI道德顾问的对话质量，让人类更愿意持续思考伦理难题。
Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations
- 提出三种不确定性对话策略：多视角、保冲突、重过程。
- 不同策略带来明显不同的对话模式，但对立场改变量影响不大。
- 叙事型角色提示更真实反映信念转变，适合研究伦理决策过程。
大型语言模型正被越来越多地用作人工道德顾问（AMA），在各种情境中提供伦理建议。本文研究了如何让AMA帮助对话者‘与不确定性共处’。提出了三种不确定性策略（视角多元、张力保留、过程反思），并与三种对照条件（基础、说服性、谄媚）进行对比。用户代理模型在伦理困境对话中与采用特定不确定性策略的AMA互动，并完成对话前后问卷。进一步考察了两种角色提示格式（陈述式与叙述式）的影响。研究发现：(1) 没有单一模型能作为理想用户代理，开放模型通过跨角色差异体现人类模糊性，封闭模型则通过角色内保守表达实现；(2) 陈述式角色提示更有效捕捉初始立场多样性，叙述式角色提示展现更真实的信念调整；(3) 六种AMA策略均产生可区分的对话模式；(4) 不同策略的差异不在于引发多少立场改变，而在于维持高质量对话互动的能力。
原文摘要 · Abstract (English)
LLMs are increasingly deployed as Artificial Moral Advisors (AMA) in a variety of contexts: what kind of conversational patterns should they display? In this paper, we study how AMA can help their interlocutors "stay with the uncertainty". We propose three modes of uncertainty (Perspective-Multiplying, Tension-Preserving, Process-Reflecting) and compare them against three control conditions (Baseline, Persuasive, Sycophantic). A user-agent LLM engages in a dialogue on an ethical dilemma with an AMA following a specific uncertainty strategy, and completes pre- and post-conversation questionnaires. We further examine the effect of two persona prompt formats (Declarative and Narrative). We found that (1) no single model dominates as a simulated user agent, with open models aligning with human ambiguity through between-persona divergence and closed models through within-persona hedging; (2) declarative personas better capture initial stance diversity while narrative personas show more realistic belief revision; (3) all six AMA strategies produce distinguishable conversational patterns; and (4) uncertainty strategies differ not in how much stance revision they produce, but in the quality of engagement they sustain.
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。