{"total":19,"rows":[{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2505.11733","title":"MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports","created":"2025-05-16","cited_by_count":36,"area":"lr"},{"id":"2412.10849","title":"Superhuman performance of a large language model on the reasoning tasks of a physician","created":"2024-12-14","cited_by_count":28,"area":"lr"},{"id":"2507.07988","title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models","created":"2025-07-10","cited_by_count":22,"area":"lr"},{"id":"2403.06294","title":"ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes","created":"2024-03-10","cited_by_count":13,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2510.11196","title":"Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations","created":"2025-10-13","cited_by_count":9,"area":"lr"},{"id":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2503.12286","title":"Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes","created":"2025-03-15","cited_by_count":7,"area":"lr"},{"id":"2504.09421","title":"ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model","created":"2025-04-13","cited_by_count":7,"area":"lr"},{"id":"2412.15748","title":"Critique of Impure Reason: Unveiling the reasoning behaviour of medical Large Language Models","created":"2024-12-20","cited_by_count":2,"area":"lr"},{"id":"2507.03001","title":"Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs","created":"2025-07-02","cited_by_count":2,"area":"lr"},{"id":"2511.04720","title":"Learning to reason about rare diseases through retrieval-augmented agents","created":"2025-11-06","cited_by_count":2,"area":"lr"},{"id":"2503.12686","title":"Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters","created":"2025-03-16","cited_by_count":1,"area":"lr"},{"id":"2604.14121","title":"Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis","created":"2026-04-15","cited_by_count":1,"area":"lr"},{"id":"2407.03004","title":"SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy","created":"2024-07-03","cited_by_count":0,"area":"lr"},{"id":"2511.20680","title":"Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes","created":"2025-11-16","cited_by_count":0,"area":"lr"},{"id":"2602.02295","title":"EvalQReason: A Framework for Step-Level Reasoning Evaluation in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2606.06869","title":"Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation","created":"2026-06-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}