{"list":"other","total":59,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"id":"1905.07854","title":"KGAT: Knowledge Graph Attention Network for Recommendation","created":"2019-05-20","cited_by_count":343},{"id":"2311.07397","title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","created":"2023-11-13","cited_by_count":300},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269},{"id":"2308.06394","title":"Detecting and Preventing Hallucinations in Large Vision Language Models","created":"2023-08-11","cited_by_count":256},{"id":"2309.07430","title":"Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization","created":"2023-09-14","cited_by_count":246},{"id":"2010.09926","title":"Explainable Automated Fact-Checking for Public Health Claims","created":"2020-10-19","cited_by_count":211},{"id":"2207.08143","title":"Can large language models reason about medical questions?","created":"2022-07-17","cited_by_count":194},{"id":"2307.15343","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","created":"2023-07-28","cited_by_count":157},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129},{"id":"2311.05656","title":"Combating Misinformation in the Age of LLMs: Opportunities and Challenges","created":"2023-11-09","cited_by_count":95},{"id":"2412.19260","title":"MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes","created":"2024-12-26","cited_by_count":80},{"id":"2005.00033","title":"Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society","created":"2020-04-30","cited_by_count":72},{"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":"2202.11684","title":"MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset","created":"2022-02-23","cited_by_count":61},{"id":"2406.10185","title":"Detecting and Evaluating Medical Hallucinations in Large Vision Language Models","created":"2024-06-14","cited_by_count":57},{"id":"2006.05557","title":"ReCOVery: A Multimodal Repository for COVID-19 News Credibility Research","created":"2020-06-09","cited_by_count":44},{"id":"2303.06433","title":"Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation","created":"2023-03-11","cited_by_count":39},{"id":"2309.08503","title":"HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking","created":"2023-09-15","cited_by_count":35},{"id":"2401.11969","title":"Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research","created":"2024-01-22","cited_by_count":35},{"id":"2311.01463","title":"Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI","created":"2023-09-26","cited_by_count":33},{"id":"2208.08408","title":"Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models","created":"2022-08-17","cited_by_count":30},{"id":"2204.12164","title":"CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweets","created":"2022-04-26","cited_by_count":29},{"id":"2402.07023","title":"Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations","created":"2024-02-10","cited_by_count":27},{"id":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26},{"id":"2305.18265","title":"Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence","created":"2023-05-29","cited_by_count":25},{"id":"2407.02730","title":"MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context","created":"2024-07-03","cited_by_count":20},{"id":"2309.04175","title":"Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese","created":"2023-09-08","cited_by_count":18},{"id":"2010.08768","title":"ArCOV19-Rumors: Arabic COVID-19 Twitter Dataset for Misinformation Detection","created":"2020-10-17","cited_by_count":15},{"id":"2203.13883","title":"Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities","created":"2022-03-25","cited_by_count":15},{"id":"2209.14901","title":"DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processing","created":"2022-09-29","cited_by_count":14},{"id":"2212.07507","title":"Artificial Intelligence for Health Message Generation: Theory, Method, and an Empirical Study Using Prompt Engineering","created":"2022-12-14","cited_by_count":14},{"id":"2109.06416","title":"MMCoVaR: Multimodal COVID-19 Vaccine Focused Data Repository for Fake News Detection and a Baseline Architecture for Classification","created":"2021-09-14","cited_by_count":12},{"id":"2010.09029","title":"CHECKED: Chinese COVID-19 Fake News Dataset","created":"2020-10-18","cited_by_count":11},{"id":"2110.14532","title":"FacTeR-Check: Semi-automated fact-checking through Semantic Similarity and Natural Language Inference","created":"2021-10-27","cited_by_count":10},{"id":"2204.12294","title":"Monant Medical Misinformation Dataset: Mapping Articles to Fact-Checked Claims","created":"2022-04-26","cited_by_count":10},{"id":"2402.01360","title":"What Makes Medical Claims (Un)Verifiable? Analyzing Entity and Relation Properties for Fact Verification","created":"2024-02-02","cited_by_count":10},{"id":"2402.18099","title":"Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models","created":"2024-02-28","cited_by_count":10},{"id":"2012.13968","title":"Detecting Medical Misinformation on Social Media Using Multimodal Deep Learning","created":"2020-12-27","cited_by_count":9},{"id":"2306.08871","title":"Med-MMHL: A Multi-Modal Dataset for Detecting Human- and LLM-Generated Misinformation in the Medical Domain","created":"2023-06-15","cited_by_count":9},{"id":"2109.11451","title":"MedKnowts: Unified Documentation and Information Retrieval for Electronic Health Records","created":"2021-09-23","cited_by_count":7},{"id":"2209.07834","title":"Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweets","created":"2022-09-16","cited_by_count":7},{"id":"2405.08373","title":"PromptMind Team at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles","created":"2024-05-14","cited_by_count":6},{"id":"2311.13878","title":"Minimizing Factual Inconsistency and Hallucination in Large Language Models","created":"2023-11-23","cited_by_count":5},{"id":"2404.14544","title":"WangLab at MEDIQA-CORR 2024: Optimized LLM-based Programs for Medical Error Detection and Correction","created":"2024-04-22","cited_by_count":4}],"next_cursor":null}