OISD improves mathematical reasoning in language models by using the final layer as an internal teacher to align logits and attention patterns in selected intermediate layers via signed advantage-weighted Jensen-Shannon divergence during GRPO optimization.
Reinforcement learning fine-tuning enhances activation intensity and diversity in the internal circuitry of llms,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
A scoping review surveying circuit analysis, sparse autoencoders, activation steering, and neurosymbolic frameworks for interpreting and controlling Transformer-based neural networks.
citing papers explorer
-
OISD: On-Policy Internal Self-Distillation of Language Models
OISD improves mathematical reasoning in language models by using the final layer as an internal teacher to align logits and attention patterns in selected intermediate layers via signed advantage-weighted Jensen-Shannon divergence during GRPO optimization.
-
Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
A scoping review surveying circuit analysis, sparse autoencoders, activation steering, and neurosymbolic frameworks for interpreting and controlling Transformer-based neural networks.