3 papers
cs.LG2026
Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
Kundan Krishna, Joseph Y Cheng, Charles Maalouf +1
Existing paradigms for ensuring AI safety, such as guardrail models and alignment training, often compromise either inference efficiency or development flexibility. We introduce Di…
cs.CV2025
SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation
Alec Helbling, Shruti Palaskar, Kundan Krishna +3
What exactly makes a particular image unsafe? Systematically differentiating between benign and problematic images is a challenging problem, as subtle changes to an image, such as…
cs.CL2025
Learning to Reason for Hallucination Span Detection
Hsuan Su, Ting-Yao Hu, Hema Swetha Koppula +7
Large language models (LLMs) often generate hallucinations -- unsupported content that undermines reliability. While most prior works frame hallucination detection as a binary task…