作者位次 #5/9ACL 2026Poster· Natural Language Processing
Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
Hao Wang · Hao Gu · Hongming Piao · Kaixiong Gong · Yuxiao Ye · Xiangyu Yue · Sirui Han · Yike Guo · Dapeng Wu
摘要
The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with...