Consensus as Privileged Context for Label-Free Self-Distillation

• URL: http://arxiv.org/abs/2607.13643v1
• Date: Wed, 15 Jul 2026 09:39:32 GMT
• Title: Consensus as Privileged Context for Label-Free Self-Distillation
• Abstract summary: CANON (Consensus-ANchored self-distillatiON) is a label-free training method that turns consensus into dense, token-level supervision.<n>CanON improves pass@1 by up to 12 points, outperforming label-free reinforcement learning by 6 points at a seventh of its compute.
• Score: 12.523025093871304
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sampling multiple solutions and returning the majority answer is among the most reliable ways to improve the reasoning accuracy of large language models without labels, and a growing family of methods converts this consensus signal into training supervision. However, existing approaches use consensus only in restricted forms: as a filter that selects solutions for fine-tuning, as a preference between answers, or as a scalar reward for reinforcement learning, discarding most of the information that the agreeing solutions contain. We present CANON (Consensus-ANchored self-distillatiON), a label-free training method that turns consensus into dense, token-level supervision. For each unlabeled prompt, CANON samples multiple solutions, extracts the majority answer, and conditions a frozen snapshot of the model on a solution that reaches it; this consensus-anchored teacher then supervises the model on its own rollouts at every token. Experiments on mathematical and scientific reasoning benchmarks show that CANON improves pass@1 by up to 12 points, outperforming label-free reinforcement learning by 6 points at a seventh of its compute and approaching a teacher conditioned on gold solutions; trained on pooled unlabeled data, it transfers to held-out benchmarks, matching training methods that use gold labels. Analysis suggests that the improvements are not pure distribution sharpening: after training, the model solves problems it previously never solved in 32 attempts, and its majority vote itself becomes more accurate.

Related papers

• Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline [56.53954182896384]
  We propose Self-Verified Distillation, a simple post-training refinement algorithm for large language models.<n>Self-Verified Distillation generates candidate solutions to unlabeled seed questions.<n>It filters them using prompt-based self-verification, and trains on the resulting self-curated dataset.<n>We find that sampling more candidate generations and using a larger verification budget during training data construction produces higher-quality self-curated data.
  arXiv  Detail & Related papers  (2026-05-20T17:26:10Z)
• 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)
• A Single Revision Step Improves Token-Efficient LLM Reasoning [3.344806691289323]
  We introduce Packet-Conditioned Revision (PACER), a training-free, inference-only framework for large language models.<n>PACER enables reasoning traces to revise their conclusions through a structured coordination step.<n>On challenging competitive math benchmarks, PACER matches or exceeds the accuracy of 256-sample majority voting.
  arXiv  Detail & Related papers  (2026-02-02T21:28:42Z)
• Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning [48.14470449860784]
  Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference.<n>We introduce Self-Harmony, a framework built on a simple intuition.
  arXiv  Detail & Related papers  (2025-11-03T03:34:34Z)
• Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers [63.99316853136304]
  Mirror-Critique is a framework that trains a verifier with informative critiques.<n>We deploy a small instruction-tuned model to synthesize high-quality critique data.<n>The resulting Mirror-Verifier is deployed to evaluate candidate solutions by generating multiple critiques per solution.
  arXiv  Detail & Related papers  (2025-09-27T06:50:24Z)
• The Majority is not always right: RL training for solution aggregation [53.1050856072799]
  We train an aggregator model to review, reconcile, and synthesize a final, correct answer.<n>A key ingredient is careful balancing of easy and hard training examples.<n>We find our method, AggLM, outperforms both strong rule-based and reward-model baselines.
  arXiv  Detail & Related papers  (2025-09-08T16:39:38Z)
• Rationale-Aware Answer Verification by Pairwise Self-Evaluation [11.763229353978321]
  We show that training reliable verifiers requires ensuring the validity of rationales in addition to the correctness of the final answers. Our results suggest that training reliable verifiers requires ensuring the validity of rationales in addition to the correctness of the final answers.
  arXiv  Detail & Related papers  (2024-10-07T08:53:00Z)
• A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering [60.768146126094955]
  Weakly supervised question answering usually has only the final answers as supervision signals. There may exist many spurious solutions that coincidentally derive the correct answer, but training on such solutions can hurt model performance. We propose to explicitly exploit such semantic correlations by maximizing the mutual information between question-answer pairs and predicted solutions.
  arXiv  Detail & Related papers  (2021-06-14T05:47:41Z)

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.