Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization
arXiv:2610.12855v1 Announce Type: new Abstract: On-Policy Self-distillation is a self-improvement paradigm that enables large language models (LLMs) to improve their capabilities by leveraging the same model as both teacher and student under different conditioning contexts. However, we find that OP…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-12 04:00 · arXiv cs.AI
Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization