Fine-tuning reasoning models on answer-only data induces reasoning-trace collapse where valid traces disappear while answer performance stays high, and simple loss-masking can mitigate it.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
COPSD improves mathematical reasoning in low-resource languages by having LLMs self-distill from their own high-resource English behavior via token-level divergence on rollouts with privileged crosslingual context.
citing papers explorer
-
Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning
Fine-tuning reasoning models on answer-only data induces reasoning-trace collapse where valid traces disappear while answer performance stays high, and simple loss-masking can mitigate it.
-
Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
COPSD improves mathematical reasoning in low-resource languages by having LLMs self-distill from their own high-resource English behavior via token-level divergence on rollouts with privileged crosslingual context.