A trajectory for student-LLM distillation is better when its tokens are surprising but still high-ranked, and the ratio of average rank to average surprisal (RSR) selects such trajectories better than existing metrics.
Rethinking the generation of high-quality cot data from the perspective of llm-adaptive question difficulty grading.CoRR, abs/2504.11919
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
citing papers explorer
-
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
A trajectory for student-LLM distillation is better when its tokens are surprising but still high-ranked, and the ratio of average rank to average surprisal (RSR) selects such trajectories better than existing metrics.
- The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes