Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
arXiv:2606.26366v1 Announce Type: new Abstract: 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
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2606.26366 (cs) [Submitted on 24 Jun 2026] Title:Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models Authors:Patrick Cooper, Alvaro Velasquez View a PDF of the paper titled Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models, by Patrick Cooper and 1 other authors View PDF HTML (experimental) Abstract: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).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
