{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"2203.03540","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","created":"2022-02-02","cited_by_count":238},{"id":"1802.05695","title":"Explainable Prediction of Medical Codes from Clinical Text","created":"2018-02-15","cited_by_count":234},{"id":"2403.11549","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","created":"2024-03-18","cited_by_count":199},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163},{"id":"1811.01727","title":"AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification","created":"2018-11-01","cited_by_count":102},{"id":"2310.01427","title":"Attention Sorting Combats Recency Bias In Long Context Language Models","created":"2023-09-28","cited_by_count":90},{"id":"1912.00862","title":"ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network","created":"2019-11-25","cited_by_count":73},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67},{"id":"2203.01515","title":"Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding","created":"2022-03-03","cited_by_count":53},{"id":"2010.05878","title":"PECOS: Prediction for Enormous and Correlated Output Spaces","created":"2020-10-12","cited_by_count":50},{"id":"2204.06683","title":"Revisiting Transformer-based Models for Long Document Classification","created":"2022-04-14","cited_by_count":49},{"id":"2207.05289","title":"PLM-ICD: Automatic ICD Coding with Pretrained Language Models","created":"2022-07-12","cited_by_count":49},{"id":"2304.10909","title":"Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study","created":"2023-04-21","cited_by_count":49},{"id":"2007.06351","title":"A Label Attention Model for ICD Coding from Clinical Text","created":"2020-07-13","cited_by_count":48},{"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},{"id":"2106.02524","title":"CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes","created":"2021-06-04","cited_by_count":20},{"id":"2304.13998","title":"Mimic-IV-ICD: A new benchmark for eXtreme MultiLabel Classification","created":"2023-04-27","cited_by_count":19},{"id":"2402.15700","title":"CoRelation: Boosting Automatic ICD Coding Through Contextualized Code Relation Learning","created":"2024-02-24","cited_by_count":18},{"id":"2211.13813","title":"Multi-label Few-shot ICD Coding as Autoregressive Generation with Prompt","created":"2022-11-24","cited_by_count":17},{"id":"2307.00067","title":"Transformers in Healthcare: A Survey","created":"2023-06-30","cited_by_count":17},{"id":"2310.06552","title":"Automated clinical coding using off-the-shelf large language models","created":"2023-10-10","cited_by_count":14},{"id":"2401.13512","title":"Can GPT-3.5 Generate and Code Discharge Summaries?","created":"2024-01-24","cited_by_count":13},{"id":"2211.00640","title":"CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification","created":"2022-10-29","cited_by_count":12},{"id":"2406.08958","title":"An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records","created":"2024-06-13","cited_by_count":12},{"id":"2204.10408","title":"ICDBigBird: A Contextual Embedding Model for ICD Code Classification","created":"2022-04-21","cited_by_count":10},{"id":"2109.07319","title":"InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification","created":"2021-09-13","cited_by_count":8},{"id":"2405.19093","title":"Multi-stage Retrieve and Re-rank Model for Automatic Medical Coding Recommendation","created":"2024-05-29","cited_by_count":8},{"id":"2302.12666","title":"Modelling Temporal Document Sequences for Clinical ICD Coding","created":"2023-02-24","cited_by_count":7},{"id":"2310.10636","title":"Dual-Encoders for Extreme Multi-Label Classification","created":"2023-10-16","cited_by_count":7},{"id":"2312.11276","title":"Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach","created":"2023-12-18","cited_by_count":7},{"id":"2305.12749","title":"A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches","created":"2023-05-22","cited_by_count":6},{"id":"2311.13735","title":"Surpassing GPT-4 Medical Coding with a Two-Stage Approach","created":"2023-11-22","cited_by_count":6},{"id":"2311.09649","title":"ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification","created":"2023-11-16","cited_by_count":5},{"id":"2304.01969","title":"MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities","created":"2023-04-04","cited_by_count":4},{"id":"2310.09672","title":"Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive Learning","created":"2023-10-14","cited_by_count":4},{"id":"2409.10504","title":"DILA: Dictionary Label Attention for Mechanistic Interpretability in High-dimensional Multi-label Medical Coding Prediction","created":"2024-09-16","cited_by_count":4},{"id":"2308.13139","title":"MatchXML: An Efficient Text-label Matching Framework for Extreme Multi-label Text Classification","created":"2023-08-25","cited_by_count":3},{"id":"2405.04545","title":"Learning label-label correlations in Extreme Multi-label Classification via Label Features","created":"2024-05-03","cited_by_count":3},{"id":"2405.19084","title":"Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification","created":"2024-05-29","cited_by_count":3},{"id":"2404.11132","title":"A Novel ICD Coding Method Based on Associated and Hierarchical Code Description Distillation","created":"2024-04-17","cited_by_count":1}],"next_cursor":null}