AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Medical Interpretability and Knowledge Maps of Large Language Models

Razvan Marinescu, Victoria-Elisabeth Gruber, Diego Fajardo V.

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
compare drug grouping by medical specialty vs mechanism of actionLlama3.3-70B · Drugs UMAP (best layer)Silhouette: 0.07 -> 0.19Improved
compare drug grouping by specialty vs mechanismGPT-OSS-120B · Drugs UMAP (best layer)Silhouette: 0.07 vs 0.07No clear effect
lesion layers in Gemma/MedGemma versus other models (ablation)Gemma3-27B / MedGemma-27B · Layer lesioningresponse degradationHurt
compare representations at best layer vs last layer for ageQwen-32B · Age linearitylinear R2: 0.99 -> 0.59Hurt
compare Gemma/MedGemma to Llama and Qwen on symptom clusteringGemma3-27B · Symptoms UMAP (best layer)Silhouette: 0.19 (Llama) vs -0.10Hurt
medical fine-tuning (MedGemma) over Gemma3MedGemma-27B · Symptoms UMAP (best layer)Silhouette: -0.10 -> -0.08No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy