Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

Source

arXiv

arxiv.org/abs/2607.02460v1

Read the source

Source

Plain-Language Brief

Researchers propose a new method called Neuron On-Policy Self-Distillation (Neuron-OPSD) for training large language models without human annotations in specialized domains where they are costly to obtain. This method uses the internal neuron activations of the model to guide data selection and teacher context construction, and it improves in-domain task performance while preserving cross-domain generalization and mitigating calibration collapse compared to prior annotation-free baselines.

What the Document Says

  • The paper proposes a new method called Neuron On-Policy Self-Distillation (Neuron-OPSD).
  • It is designed for training large language models without human annotations in specialized domains where they are costly to obtain.
  • The method uses the internal neuron activations of the model to guide 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.

Key Concepts Mentioned

  • Neuron On-Policy Self-Distillation (Neuron-OPSD)
  • large language models
  • annotation-free self-distillation
  • specialized domains
  • neuron activations
  • on-policy distillation

Claims Made by the Document

  • Neuron-OPSD improves in-domain task performance.
  • Neuron-OPSD preserves cross-domain generalization.
  • Neuron-OPSD mitigates calibration collapse.

Evidence Used

  • 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.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.