Research COLM 2026Minimal, Local, Causal Explanations for Jailbreak Success in Large Language ModelsShubham Kumar, Narendra Ahuja ProjectPaperCodePoster CVPR 2026Measuring the (Un)Faithfulness of Concept-Based ExplanationsShubham Kumar, Narendra Ahuja ProjectPaperCodeVideoPoster
COLM 2026Minimal, Local, Causal Explanations for Jailbreak Success in Large Language ModelsShubham Kumar, Narendra Ahuja ProjectPaperCodePoster
CVPR 2026Measuring the (Un)Faithfulness of Concept-Based ExplanationsShubham Kumar, Narendra Ahuja ProjectPaperCodeVideoPoster
