Research map / Large language models / Retrieval and knowledge
From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas
Zhaokun Yan, Shan Xu, Wuzheng Dong, Zhaohan Liu, Lijie Feng, Chengxiao Dai, Chen Tianqi, Binfan Liu, Yunpu Ma, Wenting Wei, Yingting Li, Yi Zhang and 1 more
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 |
|---|---|---|---|
| add SFT on GlobalHealthAtlas (ablation) | qwen3-4b · GlobalHealthAtlas | score: 5.773 -> 6.382 | Improved |
| add SFT on GlobalHealthAtlas (ablation) | qwen3.5-122B-A10B · Instruction-public-health-dataset | score: 4.199 -> 6.669 | Improved |
| add SFT on GlobalHealthAtlas (ablation) | qwen3-8b · GlobalHealthAtlas | score: 6.490 -> 6.532 | No clear effect |
| add SFT on GlobalHealthAtlas (ablation) | qwen3-8b · publichealth-qa | score: 6.075 -> 5.652 | Hurt |
| add SFT on GlobalHealthAtlas (ablation) | Llama-3.2-3B-Instruct · MedQA | score: 6.326 -> 6.235 | Hurt |
| add SFT on GlobalHealthAtlas (ablation) | Llama-3.3-70B-Instruct · MedQA | score: 6.266 -> 7.937 | Improved |
| increase SFT data from 60% to 100% (ablation) | qwen3-14b · GlobalHealthAtlas | score: 6.5748 -> 6.5648 | No clear effect |
| add SFT data 10% (vs none) (ablation) | qwen3-8b · GlobalHealthAtlas | score: 6.4896 -> 6.4185 | Hurt |
| add SFT on GlobalHealthAtlas (ablation) | qwen3-14b · GPQA | score: 5.277 -> 5.723 | Improved |
| add SFT on GlobalHealthAtlas (ablation) | qwen3-14b · MMLU-pro | score: 7.426 -> 7.309 | Hurt |
| add 0.85 weight interpolation between SFT and base (ablation) | qwen3-14b SFT · MMLU-pro | score: 7.309 -> 7.545 | Improved |
| use uniform instead of expert quality weights (ablation) | Quality gate scoring · Weighting sensitivity (SC format) | Kendall tau: 0.930 -> 0.775 | Hurt |
Closest papers by meaning
- Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews (NeurIPS 2026 · similarity 0.85)
- MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models (NeurIPS 2024 · similarity 0.85)
- OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning (CVPR 2026 · similarity 0.84)
- Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks (NeurIPS 2026 · similarity 0.84)
- Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias (NeurIPS 2024 · similarity 0.84)
- CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research (NeurIPS 2025 · similarity 0.84)
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.
