{"list":"other","total":78,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1705.02315","title":"ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","created":"2017-05-05","cited_by_count":972},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"1804.05685","title":"A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents","created":"2018-04-16","cited_by_count":478},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"1901.09192","title":"SelectiveNet: A Deep Neural Network with an Integrated Reject Option","created":"2019-01-26","cited_by_count":350},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"1811.09621","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","created":"2018-11-22","cited_by_count":297},{"id":"1811.12823","title":"Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models","created":"2018-11-29","cited_by_count":275},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231},{"id":"2307.00589","title":"MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval","created":"2023-07-02","cited_by_count":185},{"id":"2305.13523","title":"A Study of Generative Large Language Model for Medical Research and Healthcare","created":"2023-05-22","cited_by_count":163},{"id":"2004.03329","title":"MedDialog: Two Large-scale Medical Dialogue Datasets","created":"2020-04-07","cited_by_count":161},{"id":"2401.06775","title":"Large language models in healthcare and medical domain: A review","created":"2023-12-12","cited_by_count":127},{"id":"2306.02022","title":"ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation","created":"2023-06-03","cited_by_count":118},{"id":"2401.13835","title":"What Large Language Models Know and What People Think They Know","created":"2024-01-24","cited_by_count":110},{"id":"2106.08087","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","created":"2021-06-15","cited_by_count":101},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"2402.09742","title":"AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator","created":"2024-02-15","cited_by_count":101},{"id":"2403.18421","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","created":"2024-03-27","cited_by_count":86},{"id":"2204.04263","title":"BioRED: A Rich Biomedical Relation Extraction Dataset","created":"2022-04-08","cited_by_count":85},{"id":"2308.06834","title":"Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine","created":"2023-08-13","cited_by_count":83},{"id":"2104.06486","title":"MS2: Multi-Document Summarization of Medical Studies","created":"2021-04-13","cited_by_count":80},{"id":"2411.06037","title":"Sufficient Context: A New Lens on Retrieval Augmented Generation Systems","created":"2024-11-09","cited_by_count":72},{"id":"2406.12036","title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","created":"2024-06-17","cited_by_count":70},{"id":"2405.02559","title":"A Framework for Human Evaluation of Large Language Models in Healthcare Derived from Literature Review","created":"2024-05-04","cited_by_count":66},{"id":"2505.23802","title":"MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks","created":"2025-05-26","cited_by_count":64},{"id":"2506.12469","title":"Levels of Autonomy for AI Agents","created":"2025-06-14","cited_by_count":48},{"id":"2010.07497","title":"MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation","created":"2020-10-15","cited_by_count":45},{"id":"2407.01032","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","created":"2024-07-01","cited_by_count":37},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32},{"id":"2403.13313","title":"Polaris: A Safety-focused LLM Constellation Architecture for Healthcare","created":"2024-03-20","cited_by_count":28},{"id":"2406.13890","title":"ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World","created":"2024-06-19","cited_by_count":28},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28},{"id":"2311.09702","title":"Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?","created":"2023-11-16","cited_by_count":26},{"id":"2108.05067","title":"Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning","created":"2021-08-11","cited_by_count":24},{"id":"2505.22919","title":"ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Room","created":"2025-05-28","cited_by_count":22},{"id":"2509.19319","title":"FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering","created":"2025-09-12","cited_by_count":22},{"id":"2104.09632","title":"Searching for Scientific Evidence in a Pandemic: An Overview of TREC-COVID","created":"2021-04-19","cited_by_count":19},{"id":"2404.00205","title":"Conceptual and Unbiased Reasoning in Language Models","created":"2024-03-30","cited_by_count":19},{"id":"2504.13861","title":"3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark","created":"2025-03-26","cited_by_count":16},{"id":"2402.00179","title":"De-identification is not enough: a comparison between de-identified and synthetic clinical notes","created":"2024-01-31","cited_by_count":14},{"id":"2405.07896","title":"Almanac Copilot: Towards Autonomous Electronic Health Record Navigation","created":"2024-04-30","cited_by_count":9},{"id":"2508.07616","title":"ThinkTuning: Instilling Cognitive Reflections without Distillation","created":"2025-08-11","cited_by_count":9},{"id":"2406.11243","title":"FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation","created":"2024-06-17","cited_by_count":8},{"id":"2503.00269","title":"Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropy","created":"2025-03-01","cited_by_count":8},{"id":"2409.03440","title":"Rx Strategist: Prescription Verification using LLM Agents System","created":"2024-09-05","cited_by_count":7},{"id":"2509.17436","title":"MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses","created":"2025-09-22","cited_by_count":6},{"id":"2509.25725","title":"Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities","created":"2025-09-30","cited_by_count":6},{"id":"2504.16273","title":"From Promising Capability to Pervasive Bias: Assessing Large Language Models for Emergency Department Triage","created":"2025-04-22","cited_by_count":5},{"id":"2506.15662","title":"CC-LEARN: Cohort-based Consistency Learning","created":"2025-06-18","cited_by_count":5},{"id":"2407.07666","title":"A Proposed S.C.O.R.E. Evaluation Framework for Large Language Models : Safety, Consensus, Objectivity, Reproducibility and Explainability","created":"2024-07-10","cited_by_count":3},{"id":"2509.10746","title":"RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems","created":"2025-09-12","cited_by_count":3},{"id":"2506.13502","title":"BOW: Training Language Models to Reason Over Plausible Next Words","created":"2025-06-16","cited_by_count":2},{"id":"2510.00414","title":"RELATE-Sim: Leveraging Turning Point Theory and LLM Agents to Predict and Understand Long-Term Relationship Dynamics through Interactive Narrative Simulations","created":"2025-10-01","cited_by_count":2}],"next_cursor":null}