Neuron-OPSD用神经元信号挑训练数据，让大模型自己教自己，不用人工标注，效果还更稳。
论文提出Neuron-OPSD框架，解决无标注自蒸馏中SFT/GRPO变体导致域外性能下降、奖励型on-policy RL校准误差扩张的问题。该框架利用模型内部神经元激活值指导训练数据选择和教师上下文构建，通过on-policy蒸馏训练。在多个专业领域基准上，Neuron-OPSD提升域内任务性能，同时保持跨域泛化并减轻校准崩溃。该方法不依赖任何真实标签或外部反馈。
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Recent annotation-free self-evolution methods address this by using the model's own outputs as supervision signals, constructing a teacher via additional context and aggregating predictions across multiple rollouts through majority voting to produce pseudo-labels. However, these approaches are not without drawbacks: SFT- and GRPO-based variants suffer out-of-domain performance degradation, while reward-based on-policy RL inflates calibration error. In this paper, we propose Neuron On-Policy Self-Distillation (Neuron-OPSD), a data-centric framework for annotation-free self-distillation that leverages internal neuron activations to guide both training-data selection and teacher context construction. The model is then trained via on-policy distillation from the teacher distribution, requiring no ground-truth labels at any stage. Across specialized-domain benchmarks, Neuron-OPSD improves in-domain task performance while preserving cross-domain generalization and mitigating calibration collapse over prior annotation-free baselines. This framework is particularly relevant to settings where online interaction or external supervision is costly or infeasible, and is conceptually distinct from offline RL approaches that rely on logged, reward-labeled trajectories.