OGLS-SD improves on-policy self-distillation stability and math reasoning performance by constructing an outcome-discriminative steering direction from contrasts between successful and failed teacher logits.
International Conference on Learning Representations , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.
citing papers explorer
-
OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
OGLS-SD improves on-policy self-distillation stability and math reasoning performance by constructing an outcome-discriminative steering direction from contrasts between successful and failed teacher logits.
-
Understanding the Mechanism of Altruism in Large Language Models
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
-
Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.