Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Daniel Khashabi

Daniel Khashabi

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

NLP×3ML×2

Frequent co-authors

Arda Uzunoglu2×
Alvin Zhang2×
Tianjian Li1×
Jingyu Zhang1×
William Jurayj1×
Xi Wang1×

Research Timeline

2026
Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher

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.

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher

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.

Self-Compacting Language Model Agents

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.

Highlighted terms show continued research focus across papers

Papers

cs.CLEmpiricalRecentJun 22, 2026

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.

View →
cs.LGcs.CLRecentMay 31, 2026

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher

Arda Uzunoglu, Alvin Zhang, Daniel Khashabi

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…

View →
cs.LGcs.CLRecentMay 31, 2026

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher

Arda Uzunoglu, Alvin Zhang, Daniel Khashabi

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…

View →