3 papers
cs.LG2026
On Optimizing Multimodal Jailbreaks for Spoken Language Models
Aravind Krishnan, Karolina Stańczak, Dietrich Klakow
As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface. S…
cs.CL2025
Value Drifts: Tracing Value Alignment During LLM Post-Training
Mehar Bhatia, Shravan Nayak, Gaurav Kamath +4
As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to…
cs.CL2025
DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
Sara Vera Marjanović, Arkil Patel, Vaibhav Adlakha +14
Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an answer for a given input, DeepSeek-R1 creat…