2 citations · 3 across the 15 of their papers we have counts for
7 papers · 1 filter
Tahakom LLM Guidelines and Recipes: From Pre-training Data to an Arabic LLM
Areej AlOtaibi, Lina Alyahya, Raghad Alshabanah +12
Large Language Models (LLMs) have significantly advanced the field of natural language processing, enhancing capabilities in both language understanding and generation across diver…
ToolTweak: An Attack on Tool Selection in LLM-based Agents
Jonathan Sneh, Ruomei Yan, Jialin Yu +6
As LLMs increasingly power agents that interact with external tools, tool use has become an essential mechanism for extending their capabilities. These agents typically select tool…
BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
Thierry Blankenstein, Jialin Yu, Zixuan Li +6
Agents backed by large language models (LLMs) increasingly rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options. This raise…
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
James Oldfield, Philip Torr, Ioannis Patras +2
Monitoring large language models' (LLMs) activations is an effective way to detect harmful requests before they lead to unsafe outputs. However, traditional safety monitors often r…
FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
Runqi Lin, Alasdair Paren, Suqin Yuan +4
The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual…
Mixture of Experts Made Intrinsically Interpretable
Xingyi Yang, Constantin Venhoff, Ashkan Khakzar +4
Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on pos…
MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
Lukas Aichberger, Alasdair Paren, Guohao Li +3
Recent advances in operating system (OS) agents have enabled vision-language models (VLMs) to directly control a user's computer. Unlike conventional VLMs that passively output tex…