reward-mis-specification

Tag

Cards List
#reward-mis-specification

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

arXiv cs.AI ↗ · 2026-08-12 Cached

The paper introduces Evaluation-Conditioned Training (ECT), a post-training framework that conditions on natural language descriptions of feedback fidelity to help LLMs generalize to stronger oversight, with proof-of-concept experiments showing improved even-handedness and reduced sycophancy.

0 favorites 0 likes
← Back to home

Submit Feedback