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

Jacob Andreas

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2ML×2NLP×1

Frequent co-authors

Zifan Carl Guo1×
Laura Ruis1×
Belinda Z. Li1×
Amiri Hayes1×
Belinda Li1×

Research Timeline

2026
Explaining Attention with Program Synthesis

The paper proposes a method to approximate the behavior of attention heads in transformer language models with executable programs.

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision

This paper explores when language models (LMs) generate faithful introspection during explanation training, finding that LMs can produce more faithful explanations from earlier checkpoints or similar models, even when their behaviors shift.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIcs.LGEmpiricalRecentJun 30, 2026

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision

Zifan Carl Guo, Laura Ruis, Jacob Andreas, Belinda Z. Li

This paper explores when language models (LMs) generate faithful introspection during explanation training, finding that LMs can produce more faithful explanations from earlier checkpoints or similar…

View →
cs.LGcs.AIEmpirical
Recent
Jun 17, 2026

Explaining Attention with Program Synthesis

Amiri Hayes, Belinda Li, Jacob Andreas

The paper proposes a method to approximate the behavior of attention heads in transformer language models with executable programs.

View →