Gjergji Kasneci
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
NLP×2ML×1Crypto×1
Frequent co-authors
Research Timeline
2026
Analysing the Safety Pitfalls of Steering Vectors
This paper systematically audits the safety implications of activation steering vectors, finding that these vectors significantly influence the success rate of jailbreak attacks by overlapping with latent refusal directions.
Consolidating Rewarded Perturbations for LLM Post-Training
The paper introduces CoRP, a gradient-free operator that consolidates the benefits of ensemble-based post-training methods into a single, deployable model update, significantly improving performance with minimal computational overhead.
Highlighted terms show continued research focus across papers
Papers
cs.CLcs.LGRecentMay 29, 2026
Consolidating Rewarded Perturbations for LLM Post-Training
The paper introduces CoRP, a gradient-free operator that consolidates the benefits of ensemble-based post-training methods into a single, deployable model update, significantly improving performance w…
View →
cs.CRcs.CLRecentMar 25, 2026