paper-with-me

Papers

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight

2026-05-29 · Can Jin, Jiakang Li, Rui Wu, Eddy Zhang, Dimitris N. Metaxas arxiv

As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, limiting both weak-to-strong generalization and scalable oversight. We study a more tractable form of weak supervision: using a weak model as a critic rather than as a labeler or judge. Instead of solving the task or selecting the correct answer, the weak critic only needs to provide a non-misleading revision direction that helps the strong model better use its own knowledge. We call this setting *weak-critic strong oversight*. We first show that weak critiques can improve frozen strong models at inference time, and that critique quality is key to this improvement. We then propose progressive on-policy critique distillation (OPCD), which filters high-quality critiques and distills critic-guided behavior into the strong model through adaptive self-teacher signals. Experiments on reasoning and alignment benchmarks show that our method improves strong models over training epochs, suggesting an effective path for scalable oversight with weak supervision.

📄 PDF Abstract BibTeX arXiv:2606.00424

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GAS: Generative Auto-bidding with Post-training Search

2024-12-22 · Yewen Li, Shuai Mao, Jingtong Gao, Nan Jiang 외

Auto-bidding is essential in facilitating online advertising by automatically placing bids on behalf of advertisers. Generative auto-bidding, which generates bids based on an adjustable condition using models like transf…

Computational EfficiencySequential Decision Making

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning

2025-10-02 · Jiashun Liu, Johan Obando-Ceron, Han Lu, Yancheng He 외 arxiv

Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely pragmatic: conventional value functions are computationally expensive to train at LL…

Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics

2019-03-11 · Denis Steckelmacher, Hélène Plisnier, Diederik M. Roijers, Ann Nowé

Value-based reinforcement-learning algorithms provide state-of-the-art results in model-free discrete-action settings, and tend to outperform actor-critic algorithms. We argue that actor-critic algorithms are limited by …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Thompson Sampling

Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration

2025-09-26 · Qinxun Bai, Yuxuan Han, Wei Xu, Zhengyuan Zhou arxiv

The actor-critic (AC) framework has achieved strong empirical success in off-policy reinforcement learning but suffers from the "moving target" problem, where the evaluated policy changes continually. Functional critics,…

Reinforcement Learning

Boosting, Voting Classifiers and Randomized Sample Compression Schemes

2024-02-05 · Arthur da Cunha, Kasper Green Larsen, Martin Ritzert

In boosting, we aim to leverage multiple weak learners to produce a strong learner. At the center of this paradigm lies the concept of building the strong learner as a voting classifier, which outputs a weighted majority…