Conformal Information Pursuit for Interactively Guiding Large Language Models Paper • 2507.03279 • Published Jul 4 • 1
Running 3 SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations 🚀 3 Eliciting LLM Hallucinations
Do LLMs "know" internally when they follow instructions? Paper • 2410.14516 • Published Oct 18, 2024 • 1
Concept Lancet: Image Editing with Compositional Representation Transplant Paper • 2504.02828 • Published Apr 3 • 16
Concept Lancet: Image Editing with Compositional Representation Transplant Paper • 2504.02828 • Published Apr 3 • 16