Label-Free Reinforcement Learning via Cross-Model Entropy

• URL: http://arxiv.org/abs/2605.29009v1
• Date: Wed, 27 May 2026 19:04:35 GMT
• Title: Label-Free Reinforcement Learning via Cross-Model Entropy
• Abstract summary: Post-training large language models with reinforcement learning are bottlenecked by the reward signal.<n>We propose Cross-Model Entropy (CME) as a label-free reward signal for RL post-training.<n>CME is continuous, training-free, and grounded in the principle that responses a verifier finds unsurprising are likely correct or high quality.
• Score: 4.404496835736175
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Post-training large language models with reinforcement learning is bottlenecked by the reward signal. Existing approaches require either ground-truth verifiable rewards, restricting training to domains with automatic correctness checks (e.g., mathematics, code execution), or human preference labels, which are expensive to collect and prone to reward hacking. Recent label-free methods replace ground-truth verifiers with self-referential signals like majority voting or token entropy over a model's own outputs, but risk reinforcing a model's own errors. In this work we propose Cross-Model Entropy (CME), the mean log-likelihood of a generator's response under a separate verifier model, as a label-free reward signal for RL post-training. CME is continuous, training-free, and grounded in the principle that responses a verifier finds unsurprising are likely correct or high quality. Because the verifier is independent of the generator, the signal cannot be gamed through self-consistency. We integrate CME into GRPO with no other changes to the training loop, extending label-free RL to open-ended instruction following -- a regime where self-referential signals are inapplicable or poorly suited. On open-ended instruction following (UltraFeedback prompts, evaluated on AlpacaEval 2.0), CME rewards beat the untrained base in head-to-head LLM-as-Judge comparisons across four model families (Qwen, Llama, Gemma, OLMo) and three training regimes (pretrained, SFT, and instruction-tuned), with tie-adjusted win rates ranging from 52.5% to 71.4%. Code will be released upon publication.

Related papers

• Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward [69.99652051809737]
  In this work, we propose Verifier-free Intrinsic Gradient-Norm Reward (VIGOR)<n>VIGOR is a simple reward that uses only the policy model itself.<n>It exhibits cross-domain transfer to code benchmarks when trained only on math data.
  arXiv  Detail & Related papers  (2026-05-11T03:15:37Z)
• Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization [74.91418266859297]
  Implicit process reward models (PRMs) provide fine-grained reward signals along the reasoning process.<n>PRMs suffer from a train-inference mismatch: training only constrains a sequence-level aggregate, whereas inference requires token-level scores to reflect local step quality.<n>We propose a novel Implicit Prefix-Value Reward Model (IPVRM), which directly learns a prefix-conditioned value function estimating the probability of eventual correctness.<n>We also propose Distribution-Level RL (DistRL), which computes TD advantages for both sampled tokens and high-probability candidate tokens.
  arXiv  Detail & Related papers  (2026-04-14T18:19:54Z)
• CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution [52.691495954442985]
  CoVerRL is a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other.<n> Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9% on mathematical reasoning benchmarks.<n>Self-verification accuracy improves from around 55% to over 85%, confirming that both capabilities genuinely co-evolve.
  arXiv  Detail & Related papers  (2026-03-18T14:38:55Z)
• Self-Calibrating Language Models via Test-Time Discriminative Distillation [18.46710400838861]
  Large language models (LLMs) are systematically overconfident on questions they often answer incorrectly.<n>We introduce $textbfSECL$ ($textbfSE$lf-$textbfC$alibrating $textbfL$anguage Models), a test-time training (TTT) pipeline that exploits this gap as label-free self-supervision.
  arXiv  Detail & Related papers  (2026-03-18T13:28:50Z)
• TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning [33.47825979936341]
  Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs)<n>We propose an effective policy optimization algorithm, TraPO, that identifies reliable unlabeled samples by matching their learning trajectory similarity to labeled ones.<n>With only 1K labeled and 3K unlabeled samples, TraPO reaches 42.6% average accuracy, surpassing the best unsupervised method trained on 45K unlabeled samples (38.3%)
  arXiv  Detail & Related papers  (2025-12-15T09:03:45Z)
• RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization [52.01526898310723]
  We introduce RESTRAIN, a self-penalizing RL framework that converts the absence of gold labels into a useful learning signal.<n>Instead of overcommitting to spurious majority votes, RESTRAIN exploits signals from the model's entire answer distribution.<n>On challenging reasoning benchmarks, RESTRAIN delivers large gains using only unlabeled data.
  arXiv  Detail & Related papers  (2025-10-02T16:24:01Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models [56.055015597319674]
  Reinforcement learning with verifiable rewards (RLVR) is effective to improve the reasoning ability of large language models (LLMs)<n>Recent self-rewarding methods investigate a label-free alternative to unlock the reasoning capabilities of LLMs.<n>We propose textitCo-rewarding, a novel self-supervised RL framework that improves training stability by seeking complementary supervision from another views.
  arXiv  Detail & Related papers  (2025-08-01T08:09:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.