{"url":"/task/clinical-knowledge","name":"Clinical Knowledge","slug":"clinical-knowledge","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":133,"papers_with_code":54,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/clinical-knowledge-on-big-bench","slug":"clinical-knowledge-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":1,"metrics":["Accuracy "],"first_row_in_archive_order":{"model":"Gopher-280B (few-shot, k=5)","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_url":"/paper/scaling-language-models-methods-analysis-1","paper_date":"2021-12-08","arxiv_id":"2112.11446","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"syntology":null}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":54,"tagged_in_all":133,"items":[{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/mask-of-truth-model-sensitivity-to-unexpected","title":"Mask of truth: model sensitivity to unexpected regions of medical images","date":"2024-12-05","arxiv_id":"2412.04030","repositories_listed":2,"syntology":null},{"url":"/paper/insightbuddy-ai-medication-extraction-and","title":"INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Large Language Models and Ensemble Learning","date":"2024-09-28","arxiv_id":"2409.19467","repositories_listed":2,"syntology":null},{"url":"/paper/zero-shot-ecg-classification-with-multimodal","title":"Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement","date":"2024-03-11","arxiv_id":"2403.06659","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/inherently-interpretable-multi-label","title":"Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals","date":"2023-03-01","arxiv_id":"2303.00500","repositories_listed":2,"syntology":null},{"url":"/paper/reducing-annotation-need-in-self-explanatory","title":"Reducing Annotation Need in Self-Explanatory Models for Lung Nodule Diagnosis","date":"2022-06-27","arxiv_id":"2206.13608","repositories_listed":2,"syntology":null},{"url":"/paper/claim-clinically-guided-lge-augmentation-for","title":"CLAIM: Clinically-Guided LGE Augmentation for Realistic and Diverse Myocardial Scar Synthesis and Segmentation","date":"2025-06-18","arxiv_id":"2506.15549","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-based-counterfactual-augmentation","title":"Diffusion-based Counterfactual Augmentation: Towards Robust and Interpretable Knee Osteoarthritis Grading","date":"2025-06-18","arxiv_id":"2506.15748","repositories_listed":1,"syntology":null},{"url":"/paper/towards-generating-more-interpretable","title":"Towards generating more interpretable counterfactuals via concept vectors: a preliminary study on chest X-rays","date":"2025-06-04","arxiv_id":"2506.04058","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-list-wise-alignment-for","title":"Fine-grained List-wise Alignment for Generative Medication Recommendation","date":"2025-05-26","arxiv_id":"2505.20218","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/make-multi-aspect-knowledge-enhanced-vision","title":"MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment","date":"2025-05-14","arxiv_id":"2505.09372","repositories_listed":1,"syntology":null},{"url":"/paper/biomed-dpt-dual-modality-prompt-tuning-for","title":"Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models","date":"2025-05-08","arxiv_id":"2505.05189","repositories_listed":1,"syntology":null},{"url":"/paper/clinical-knowledge-in-llms-does-not-translate","title":"Clinical knowledge in LLMs does not translate to human interactions","date":"2025-04-26","arxiv_id":"2504.18919","repositories_listed":1,"syntology":null},{"url":"/paper/clinkd-cross-modal-clinical-knowledge","title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","date":"2025-02-09","arxiv_id":"2502.05928","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gap-enhancing-llm-performance","title":"Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments","date":"2024-12-16","arxiv_id":"2412.12417","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-machine-learning-models-against","title":"Evaluating Machine Learning Models against Clinical Protocols for Enhanced Interpretability and Continuity of Care","date":"2024-11-05","arxiv_id":"2411.03105","repositories_listed":1,"syntology":null},{"url":"/paper/a-holistic-weakly-supervised-approach-for","title":"SmoothSegNet: A Global-Local Framework for Liver Tumor Segmentation with Clinical KnowledgeInformed Label Smoothing","date":"2024-10-13","arxiv_id":"2410.10005","repositories_listed":1,"syntology":null},{"url":"/paper/climedbench-a-large-scale-chinese-benchmark","title":"CliMedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models in Clinical Scenarios","date":"2024-10-04","arxiv_id":"2410.03502","repositories_listed":1,"syntology":null},{"url":"/paper/fundus2video-cross-modal-angiography-video","title":"Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance","date":"2024-08-27","arxiv_id":"2408.15217","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02865","title":"VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge","date":"2024-08-05","arxiv_id":"2408.02865","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/ai-enhanced-7-point-checklist-for-melanoma","title":"AI-Enhanced 7-Point Checklist for Melanoma Detection Using Clinical Knowledge Graphs and Data-Driven Quantification","date":"2024-07-23","arxiv_id":"2407.16822","repositories_listed":1,"syntology":null},{"url":"/paper/open-world-electrocardiogram-classification","title":"Open-World Electrocardiogram Classification via Domain Knowledge-Driven Contrastive Learning","date":"2024-07-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/integrating-clinical-knowledge-into-concept","title":"Integrating Clinical Knowledge into Concept Bottleneck Models","date":"2024-07-09","arxiv_id":"2407.06600","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-holistic-framework-for-multimodal","title":"Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report Generation","date":"2024-07-02","arxiv_id":"2407.02235","repositories_listed":1,"syntology":null},{"url":"/paper/panacea-a-foundation-model-for-clinical-trial","title":"Panacea: A foundation model for clinical trial search, summarization, design, and recruitment","date":"2024-06-25","arxiv_id":"2407.11007","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/attri-net-a-globally-and-locally-inherently","title":"Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals","date":"2024-06-08","arxiv_id":"2406.05477","repositories_listed":1,"syntology":null},{"url":"/paper/m-qalm-a-benchmark-to-assess-clinical-reading","title":"M-QALM: A Benchmark to Assess Clinical Reading Comprehension and Knowledge Recall in Large Language Models via Question Answering","date":"2024-06-06","arxiv_id":"2406.03699","repositories_listed":1,"syntology":null},{"url":"/paper/multiple-choice-questions-and-large-languages","title":"Multiple Choice Questions and Large Languages Models: A Case Study with Fictional Medical Data","date":"2024-06-04","arxiv_id":"2406.02394","repositories_listed":1,"syntology":null},{"url":"/paper/clinical-domain-knowledge-derived-template","title":"Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification","date":"2024-03-26","arxiv_id":"2403.18871","repositories_listed":1,"syntology":null},{"url":"/paper/neural-machine-translation-of-clinical-text","title":"Neural Machine Translation of Clinical Text: An Empirical Investigation into Multilingual Pre-Trained Language Models and Transfer-Learning","date":"2023-12-12","arxiv_id":"2312.07250","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}