reward-signal

Tag

Cards List
#reward-signal

Demystifying Reinforcement Learning Post-Training of Language Models

arXiv cs.LG · 2d ago Cached

This paper deconstructs the reinforcement learning post-training algorithm for large language models, examining how base model distribution, reward signal granularity, and prompt diversity affect post-training outcomes.

0 favorites 0 likes
#reward-signal

Closing the Loop: Formally Verified Law as a Reward Signal for Self-Improving Legal AI

arXiv cs.LG · 2026-06-24 Cached

This paper presents an architecture that uses formally verified law as a reward signal for training legal AI, adaptively autoformalizing legal rules into a formal calculus and employing a verifier to ensure provable correctness, demonstrated on German and US law examples.

0 favorites 0 likes
#reward-signal

Label-Free Reinforcement Learning via Cross-Model Entropy

arXiv cs.LG · 2026-05-29 Cached

Proposes Cross-Model Entropy (CME) as a label-free reward signal for reinforcement learning post-training of large language models, enabling open-ended instruction following without ground-truth verifiers or human preference labels.

0 favorites 0 likes
← Back to home

Submit Feedback