Clinical Concept Centers in LLMs
Large language models are increasingly used in clinical settings. However, research into the reliability and performance of these models has focused almost entirely on the language substrate, scoring what the model says. Mechanistic interpretability has found that the latent space carries a higher fidelity of represent...
Aishik Nagar, A. Vaidyanathan, Arun-Kumar Kaliya-Perumal et al.
· 0 citations