activity
20222026
most cited"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks

27 citations · 37 across the 15 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CL2026

MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation

Pia Chouayfati, Alexander M. Fichtl, Miriam Anschütz +2

Clinical diagnosis is fundamentally interactive and incremental, yet the dominant paradigm for evaluating Large Language Models (LLMs) in medicine remains static QA benchmarks or t…