AINeutralarXiv – CS AI · 14h ago6/10
🧠
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
Researchers identify harmful continuation in long chain-of-thought training data where LLMs continue reasoning after the answer is sufficiently supported, degrading fine-tuning performance. Using a delete-only editor, they remove post-conclusion continuations and demonstrate improved SFT outcomes, introducing Harmful Continuation Cut (HCC) as a lightweight solution to detect and eliminate this problematic pattern.