Self-Training for Language Models

Overview

Self-training studies how language models can improve by learning from text, solutions, critiques, or trajectories they generate, often using unlabeled prompts or user and environment feedback. Common approaches include confidence- or consensus-based pseudo-labeling, self-distillation, preference and reinforcement learning, verifier-guided training, and curricula that target model weaknesses; some adapt model weights at test time. Evaluations often focus on mathematical and code reasoning, tool use, long-context tasks, translation, and safety, using exact-answer, execution, or task-success benchmarks. The central challenge is distinguishing useful learning from reinforced errors, reduced diversity, bias, or gains caused by weak evaluation, so independent verification and stable stopping criteria remain important.

Latest papers

CardsList

95 papers12 papers in the last four weeks, down 40% on the four weeks before. 0.1% of all new papers.

  1. Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion

    Feb 25, 2026Yexing Du, Youcheng Pan, Zekun Wang +7Multimodal MTMachine Translation

  2. Aligning Language Models from User Interactions

    Feb 18, 2026Thomas Kleine Buening, Jonas Hübotter, Barna Pásztor +3LLM AlignmentPersonalized Language Model Alignment

  3. Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs

    Jan 31, 2026Md Tanvirul Alam, Aritran Piplai, Ionut Cardei +2LLMs for CybersecurityReinforcement Learning with Verifiable Rewards

  4. Self-Improving Training & Thinking

    Jan 29, 2026Ellen Xiaoqing Tan, Jack Lanchantin, Zichun Yu +11Mid-Training for Language ModelsLLM Training

  5. A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning

    Oct 21, 2025Mengqi Li, Lei Zhao, Anthony Man-Cho So +2Self-Training for Language ModelsMathematical Reasoning