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

Olga E. Sorokoletova

1 indexed paper

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

Publications per year

1
26

Top categories

Society×1Crypto×1HCI×1

Frequent co-authors

Francesco Giarrusso1×
Vincenzo Suriani1×
Daniele Nardi1×

Research Timeline

2026
Learning from Mistakes: Can LLM Self-Recover after Misalignment?

This paper shifts the focus of LLM safety from preventing misalignment to investigating the model's intrinsic ability to self-recover its alignment after being corrupted by adversarial inputs.

Highlighted terms show continued research focus across papers

Papers

cs.CYcs.CRcs.HCRecentMar 25, 2026

Learning from Mistakes: Can LLM Self-Recover after Misalignment?

Olga E. Sorokoletova, Francesco Giarrusso, Vincenzo Suriani, Daniele Nardi

This paper shifts the focus of LLM safety from preventing misalignment to investigating the model's intrinsic ability to self-recover its alignment after being corrupted by adversarial inputs.

View →