Does a model's stated reason for rejecting a candidate do any work?

Paper recorded by Signals 4 on 2026-09-24 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-24 on arXiv · recorded by Signals 4 on 2026-09-25

Category: cs.AI · 人工智能 · first seen 2026-09-25

Abstract

Asked to choose between candidates and explain the choice, a language model often rejects a rival by naming a fact its profile lacks: no director, no date of death. That sentence is a claim about the text in front of the model, and it can be tested without any judge. We insert a real corpus sentence stating the named fact into the rival's profile and ask again under greedy decoding. Two controls s

Read on arXiv →