4 papers
Sparse Autoencoders are Capable LLM Jailbreak Mitigators
Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3
Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based defense that identifies jailbrea…
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
Iuri Macocco, Pau RodrÃguez, Arno Blaas +3
Controlling the output of Large Language Models (LLMs) is a central challenge for their reliable deployment, yet a clear understanding of the involved trade-offs remains elusive. C…
ReCap: Lightweight Referential Grounding for Coherent Story Visualization
Aditya Arora, Akshita Gupta, Pau Rodriguez +1
Story Visualization aims to generate a sequence of images that faithfully depicts a textual narrative that preserve character identity, spatial configuration, and stylistic coheren…
LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
Pau Rodriguez, Michal Klein, Eleonora Gualdoni +5
The growing use of generative models in daily life calls for efficient mechanisms to control their generation, to e.g., produce safe content or provide users with tools to explore…