llm-training
7 posts tagged llm-training.
- Auxiliary views explain why diverse pre-training data works
- On-policy distillation may need fewer prompts and better absorption
- BPCO Brings the Critic Back to RL Fine-Tuning
- TokEval makes tokenizer choice measurable before pretraining
- The Fifth-Grade LLM Thought Experiment: What a Capped Training Corpus Actually Reveals
- Concise answers can weaken reasoning in fused LLM training
- The Alignment Tax on Creativity, and a Switch to Turn It Back On