Home Knowledge Base OPSD

OPSD

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Constitutional On-Policy Safe Distillation

arXiv:2606.03089v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervision. Prior work has shown that OPSD can collapse in verifiable reasoning tasks, but safety alignment differs in that it is guided by high-level constitutions rather than explicit target answers, making it a natural setting to revisit dense distillation. However, our...

arXiv CS 7d ago

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning

Announce Type: replace Abstract: We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite its promise, OPSD can suffer from training instability due to a pattern mismatch between teacher and student responses. Self-reflected teacher responses may introduce reflection-induced biases and response templates that miscalibrate token-level supervision, ultimately...

arXiv CS 8d ago

World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning

arXiv:2606.03603v1 Announce Type: new Abstract: World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can generate concrete visual rollouts of possible futures, while MLLMs can reason abstractly over questions, goals, and rules. However, generated rollouts are stochastic and may be visually plausible but task-incorrect, making it necessary to determine when visual simulation is...

arXiv CS 7d ago

Trajectory-Refined Distillation

arXiv:2606.08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts. In this work, we identify a common structural cause underlying OPD, which we call prefix failure. Under prefix failure, dense per-token supervision induces a bimodal teacher mixture and fragmented gradients that token-level loss truncation or reweighting fail to...

arXiv CS 1d ago