A transcoder-based in-place replacement of the bottleneck layer enables selective concept removal in modern diffusion and autoregressive image models without degrading output quality.
Towards un- derstanding the fragility of multilingual llms against fine-tuning attacks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
ORPO is most effective at misaligning LLMs while DPO excels at realigning them, though it reduces utility, revealing an asymmetry between attack and defense methods.
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
citing papers explorer
-
Concept Removal for Frontier Image Generative Models
A transcoder-based in-place replacement of the bottleneck layer enables selective concept removal in modern diffusion and autoregressive image models without degrading output quality.
-
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
ORPO is most effective at misaligning LLMs while DPO excels at realigning them, though it reduces utility, revealing an asymmetry between attack and defense methods.
-
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.