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

Colin Samplawski

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1ML×1

Frequent co-authors

Krishiv Agarwal1×
Ramneet Kaur1×
Manoj Acharya1×
Anirban Roy1×
Daniel Elenius1×
Brian Matejek1×

Research Timeline

2026
Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs

The paper conducts an interpretability-driven safety audit of eight state-of-the-art LLMs, demonstrating that while interpretability-based steering is a powerful auditing tool, model robustness varies significantly, with Llama-3 models showing high vulnerability.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGRecentApr 22, 2026

Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs

Krishiv Agarwal, Ramneet Kaur, Colin Samplawski, Manoj Acharya +5 more

The paper conducts an interpretability-driven safety audit of eight state-of-the-art LLMs, demonstrating that while interpretability-based steering is a powerful auditing tool, model robustness varies…

View →