Paper

Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models

Unreadunread

AI summary

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).

Reading status

Priority

About this paper

Authors: Patrick Cooper, Alvaro Velasquez
Released: 2026-06-26 (13d ago)
Topic: Related to current project
Relation to my work: Read next because Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, under, token, rate, control, full, chain, language. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2606.26366

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.