Md Rysul Kabir
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
The paper investigates how different methods of jailbreaking large language models (SFT, RLVR, and abliteration) lead to vastly different behavioral and mechanistic failures, even when all methods achieve similar levels of harmful compliance.
Highlighted terms show continued research focus across papers