Daniel Khashabi
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces trust functions to filter weak supervision labels, enabling near-lossless weak-to-strong generalization by selectively training a strong student using only the most reliable weak labels.
The paper introduces trust functions to filter weak supervision labels, enabling near-lossless weak-to-strong generalization by selectively training a strong student using only the most reliable weak labels.
This paper proposes SelfCompact, a scaffold that allows models to decide when and how to compact long agent traces, improving summarization at a lower token cost.
Papers
Self-Compacting Language Model Agents
Tianjian Li, Jingyu Zhang, William Jurayj, Xi Wang +4 more
This paper proposes SelfCompact, a scaffold that allows models to decide when and how to compact long agent traces, improving summarization at a lower token cost.