Paper recorded by Signals 4 on 2026-09-25 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28
Category: cs.CL · 自然语言处理 · first seen 2026-09-28
Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningfully differ. Self-training faces the same challenge: training data is typically constructed by sampling IID responses and filtering primarily for correctness, thereby overrepresenting strategies a model already favours. We investigate strategic diver