Search papers, labs, and topics across Lattice.
2
0
5
Confident conflicts in LLM distillation are mitigated by dynamically mixing student and teacher distributions based on student entropy, boosting reasoning and preserving general capabilities.
Language models can get a 12% boost in multi-turn conversation quality from just 10k examples of multi-turn training data, highlighting the critical gap between single-turn and multi-turn capabilities.
