Reinforcement Learning for Knowledge Awareness | kalomaze's kalomazing blog
Intro If you're active at all when it comes to language model research these days, you almost certainly have an implicit mental model for what kinds of tr...
Reinforcement Learning for Knowledge Awareness – kalomaze's kalomazing blog Reinforcement Learning for Knowledge Awareness 07 May, 2026 Intro If you're active at all when it comes to language model research these days, you almost certainly have an implicit mental model for what kinds of training have been useful for capability improvement in the post-o1 era. The paradigmatic shortlist is essentially as follows: Pretraining , which targets diverse conditional prediction on natural webtext (or its synthetic derivatives). Mid-training , which targets concentrated, high quality data mixes, typical
saved by
related reading
- Illustrating Reinforcement Learning from Human Feedback (RLHF)huggingface.co
- State of RL for reasoning LLMs | A. Weersaweers.de
- [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
- RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
- RLHF | John Lambertjohnwlambert.github.io
- The State of Reinforcement Learning for LLM Reasoningmagazine.sebastianraschka.com
- SFT, RL, and On-Policy Distillation Through a Distributional Lens | whnrehiew.github.io
- 2401.10020.pdfarxiv.org
- Models Don't "Get Reward" — LessWronglesswrong.com
- Features as Rewards: Using Interpretability to Reduce Hallucinationsgoodfire.ai
- A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyondhuggingface.co
- [2506.19733] Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?arxiv.org