Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
Paper recorded by Signals 4 on 2026-10-06 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-06 on arXiv · recorded by Signals 4 on 2026-10-07
Category: cs.AI · 人工智能 · first seen 2026-10-07
Abstract
Language models increasingly act as agents. An agent that says an action is wrong and then takes it anyway is a different failure from one that does not know better, and evaluations of stated values cannot see it. We build a pre-registered panel of 248 scenarios across five kinds of pressure. Each scenario is posed twice to the same model, once as the agent choosing what to do and once in the thir
Read on arXiv →
Cite this page: Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment: the #417 most recent of 960 cs.AI papers we have recorded (as of 2026-10-06). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/principled-under-pressure-post-training-decides-whether-llms-act-on-their-own-mo.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free