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.
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 changed | Where | Measured | Effect |
|---|---|---|---|
| compare drug grouping by medical specialty vs mechanism of action | Llama3.3-70B · Drugs UMAP (best layer) | Silhouette: 0.07 -> 0.19 | Improved |
| compare drug grouping by specialty vs mechanism | GPT-OSS-120B · Drugs UMAP (best layer) | Silhouette: 0.07 vs 0.07 | No clear effect |
| lesion layers in Gemma/MedGemma versus other models (ablation) | Gemma3-27B / MedGemma-27B · Layer lesioning | response degradation | Hurt |
| compare representations at best layer vs last layer for age | Qwen-32B · Age linearity | linear R2: 0.99 -> 0.59 | Hurt |
| compare Gemma/MedGemma to Llama and Qwen on symptom clustering | Gemma3-27B · Symptoms UMAP (best layer) | Silhouette: 0.19 (Llama) vs -0.10 | Hurt |
| medical fine-tuning (MedGemma) over Gemma3 | MedGemma-27B · Symptoms UMAP (best layer) | Silhouette: -0.10 -> -0.08 | No clear effect |
Closest papers by meaning
- Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving (ICML 2025 · similarity 0.89)
- HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation (ICML 2025 · similarity 0.88)
- Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts (ICLR 2025 · similarity 0.88)
- OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning (CVPR 2026 · similarity 0.88)
- MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey (NeurIPS 2024 · similarity 0.87)
- Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks (NeurIPS 2026 · similarity 0.87)
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.
