11 papers
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck +5
Large Language Models (LLMs) exhibit impressive general-purpose capabilities but also introduce serious safety risks, particularly the potential for deception as models acquire inc…
Probing the Representational Power of Sparse Autoencoders in Vision Models
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff +4
Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse b…
Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering
Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck +4
Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots able to engage in conversations about visual inputs. However, their responses…
DPO Learning with LLMs-Judge Signal for Computer Use Agents
Man Luo, David Cobbley, Xin Su +4
Computer use agents (CUA) are systems that automatically interact with graphical user interfaces (GUIs) to complete tasks. CUA have made significant progress with the advent of lar…
Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff +4
The ImageNet hierarchy provides a structured taxonomy of object categories, offering a valuable lens through which to analyze the representations learned by deep vision models. In…
FastRM: An efficient and automatic explainability framework for multimodal generative models
Gabriela Ben-Melech Stan, Estelle Aflalo, Man Luo +5
Large Vision Language Models (LVLMs) have demonstrated remarkable reasoning capabilities over textual and visual inputs. However, these models remain prone to generating misinforma…