Similar Items: Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training
- Step Rejection Fine-Tuning: A Practical Distillation Recipe
- Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
- Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
- MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
- Patch-Effect Graph Kernels for LLM Interpretability
- How Value Induction Reshapes LLM Behaviour