{"total":48,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237,"area":null},{"id":"2212.02199","title":"Legal Prompt Engineering for Multilingual Legal Judgement Prediction","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2210.03304","title":"Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding","created":"2022-10-07","cited_by_count":40,"area":null},{"id":"2210.05529","title":"An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification","created":"2022-10-11","cited_by_count":38,"area":null},{"id":"2210.13836","title":"Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts","created":"2022-10-25","cited_by_count":24,"area":null},{"id":"2211.00974","title":"Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer","created":"2022-11-02","cited_by_count":20,"area":null},{"id":"2211.00582","title":"ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US","created":"2022-11-01","cited_by_count":17,"area":null},{"id":"2211.13813","title":"Multi-label Few-shot ICD Coding as Autoregressive Generation with Prompt","created":"2022-11-24","cited_by_count":17,"area":null},{"id":"2209.12325","title":"An Empirical Study on Cross-X Transfer for Legal Judgment Prediction","created":"2022-09-25","cited_by_count":16,"area":null},{"id":"2302.00609","title":"Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases","created":"2023-02-01","cited_by_count":14,"area":null},{"id":"2302.00768","title":"Leveraging Task Dependency and Contrastive Learning for Case Outcome Classification on European Court of Human Rights Cases","created":"2023-02-01","cited_by_count":12,"area":null},{"id":"2311.08890","title":"Large Language Models are legal but they are not: Making the case for a powerful LegalLLM","created":"2023-11-15","cited_by_count":12,"area":null},{"id":"2502.12082","title":"AdaSplash: Adaptive Sparse Flash Attention","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2402.03172","title":"Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings","created":"2024-02-05","cited_by_count":9,"area":null},{"id":"2302.12666","title":"Modelling Temporal Document Sequences for Clinical ICD Coding","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2305.16259","title":"Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2407.08330","title":"HDT: Hierarchical Document Transformer","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2405.07052","title":"Length-Aware Multi-Kernel Transformer for Long Document Classification","created":"2024-05-11","cited_by_count":5,"area":null},{"id":"2310.09672","title":"Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive Learning","created":"2023-10-14","cited_by_count":4,"area":null},{"id":"2409.15104","title":"PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2307.09532","title":"Can Model Fusing Help Transformers in Long Document Classification? An Empirical Study","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2405.18553","title":"FAIIR: Building Toward A Conversational AI Agent Assistant for Youth Mental Health Service Provision","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2507.01802","title":"The Anatomy of Evidence: An Investigation Into Explainable ICD Coding","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2211.13819","title":"Detecting Entities in the Astrophysics Literature: A Comparison of Word-based and Span-based Entity Recognition Methods","created":"2022-11-24","cited_by_count":2,"area":null},{"id":"2402.17682","title":"NextLevelBERT: Masked Language Modeling with Higher-Level Representations for Long Documents","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2408.10995","title":"CTP-LLM: Clinical Trial Phase Transition Prediction Using Large Language Models","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2307.14912","title":"ARC-NLP at PAN 2023: Hierarchical Long Text Classification for Trigger Detection","created":"2023-07-27","cited_by_count":1,"area":null},{"id":"2405.11622","title":"Continuous Predictive Modeling of Clinical Notes and ICD Codes in Patient Health Records","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2509.14942","title":"Explainable AI for Infection Prevention and Control: Modeling CPE Acquisition and Patient Outcomes in an Irish Hospital with Transformers","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2304.02886","title":"Automatic ICD-10 Code Association: A Challenging Task on French Clinical Texts","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2305.03519","title":"Leveraging BERT Language Model for Arabic Long Document Classification","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2305.07016","title":"A General-Purpose Multilingual Document Encoder","created":"2023-05-11","cited_by_count":0,"area":null},{"id":"2311.12307","title":"Causality is all you need","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2312.00513","title":"Summarization-based Data Augmentation for Document Classification","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2404.00596","title":"ECtHR-PCR: A Dataset for Precedent Understanding and Prior Case Retrieval in the European Court of Human Rights","created":"2024-03-31","cited_by_count":0,"area":null},{"id":"2408.13253","title":"Domain-specific long text classification from sparse relevant information","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2410.02930","title":"Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2410.23066","title":"Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2505.02974","title":"PLAID: A Unified Data Model for Machine Learning on Heterogeneous Physics Simulations","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2507.09897","title":"Algorithm Development in Neural Networks: Insights from the Streaming Parity Task","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.15067","title":"ROBAD: Robust Adversary-aware Local-Global Attended Bad Actor Detection Sequential Model","created":"2025-07-20","cited_by_count":0,"area":null},{"id":"2508.11092","title":"Predictive Multimodal Modeling of Diagnoses and Treatments in EHR","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2509.04471","title":"MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2510.00890","title":"Span-level Detection of AI-generated Scientific Text via Contrastive Learning and Structural Calibration","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.15267","title":"TraceCoder: Towards Traceable ICD Coding via Multi-Source Knowledge Integration","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2512.24373","title":"Skim-Aware Contrastive Learning for Efficient Document Representation","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2605.28060","title":"Challenges in Explaining Pretrained Clinical Text Classifiers","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}