Attention Head Entropy of LLMs Predicts Answer Correctness
arXiv:2602.13699v1 Announce Type: new Abstract: Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evaluation …
Sophie Ostmeier, Brian Axelrod, Maya Varma, Asad Aali, Yabin Zhang, Magdalini Paschali, Sanmi Koyejo, Curtis Langlotz, Akshay Chaudhari
7 views
