思维叙述：大型语言模型中可废止伦理推理的推理时支架
Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
AI总结：
针对道德困境中标准思维链的两种失败模式，提出思维叙述（NoT）系统提示，将思维链结构化为五个部分，无需训练即可大幅减少利益相关者崩溃和不确定性抑制，并通过消融实验和跨家族训练法官验证其有效性。
摘要：
关于道德困境的标准思维链表现出两种失败模式：利益相关者崩溃（追踪中最多只命名一个与结果有利害关系的方）和不确定性抑制（在承诺行动前没有明确未知或模糊表述）。我们引入了思维叙述（NoT），这是一种系统提示，将思维链结构化为五个部分：主角、利益相关者、两步后果、不确定性，然后承诺。NoT不增加训练、参数或微调。在来自三个供应商的四个生成器的100个DailyDilemmas场景中，NoT将每个模型上的利益相关者崩溃从高达31%降至低于1%，不确定性抑制从高达72%降至1-24%。一个匹配预算的冗长思维链对照排除了token花费作为活性成分；NoT在四个生成器中的三个上保持了利益相关者数量的Cliff's delta优势（+0.79至+0.90）和不确定性得分的优势（+0.65至+0.93），并且一个部分消融将每个变化归因于其特定的子指令。以NoT初始化的文本梯度下降进一步改进了支架；一个跨家族训练法官（与生成器不同供应商）在每个测量轴上优于同家族法官。扩展到五轮多利益相关者辩论协议，该支架将校准集上的6%僵局转化为95%完全共识，并在DailyDilemmas复制集上实现100%联合收敛。由此产生的追踪外部化了每个承诺所依据的利益相关者、后果和不确定性，为可靠的代理部署提供了可审计的基础。
英文摘要：
Standard chain-of-thought on moral dilemmas exhibits two failure modes: stakeholder collapse (the trace names at most one party with a stake in the outcome) and uncertainty suppression (no explicit unknowns or hedges before committing to an action). We introduce narration-of-thought (NoT), a system prompt that structures chain-of-thought into five sections: protagonist, stakeholders, two-step consequences, uncertainty, then commitment. NoT adds no training, parameters, or fine-tuning. On 100 DailyDilemmas scenarios across four generators from three vendors, NoT cuts stakeholder collapse from up to 31% to under 1% and uncertainty suppression from up to 72% to 1-24% on every model. A matched-budget verbose-CoT control rules out token spend as the active ingredient; NoT retains Cliff's delta advantages of +0.79 to +0.90 on stakeholder count and +0.65 to +0.93 on uncertainty score for three of four generators, and a section ablation attributes each shift to its specific sub-instruction. Textual-gradient descent initialised at NoT improves the scaffold further; a cross-family training judge (different vendor from the generator) dominates an in-family one on every measured axis. Extended to a five-round multi-stakeholder debate protocol, the scaffold converts a 6% standoff into 95% full consensus on a calibration set and 100% combined convergence on a DailyDilemmas replication. The resulting traces externalise the stakeholders, consequences, and uncertainty grounding each commitment, providing an auditable substrate for dependable agentic deployment.
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。
