{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2011.01403","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","created":"2020-11-03","cited_by_count":276},{"id":"1502.03240","title":"Conditional Random Fields as Recurrent Neural Networks","created":"2015-02-11","cited_by_count":214},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142},{"id":"2106.01223","title":"A Unified Generative Framework for Various NER Subtasks","created":"2021-06-02","cited_by_count":141},{"id":"1609.01454","title":"Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling","created":"2016-09-06","cited_by_count":137},{"id":"2306.10070","title":"Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health","created":"2023-06-15","cited_by_count":118},{"id":"1909.02188","title":"A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding","created":"2019-09-05","cited_by_count":107},{"id":"1907.00390","title":"A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling","created":"2019-06-30","cited_by_count":85},{"id":"2010.03880","title":"A Co-Interactive Transformer for Joint Slot Filling and Intent Detection","created":"2020-10-08","cited_by_count":61},{"id":"1809.00385","title":"Zero-shot User Intent Detection via Capsule Neural Networks","created":"2018-09-02","cited_by_count":54},{"id":"2103.03095","title":"A Survey on Spoken Language Understanding: Recent Advances and New Frontiers","created":"2021-03-04","cited_by_count":53},{"id":"2310.14151","title":"PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain","created":"2023-10-22","cited_by_count":40},{"id":"2109.12575","title":"Paradigm Shift in Natural Language Processing","created":"2021-09-26","cited_by_count":39},{"id":"2106.01925","title":"GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling","created":"2021-06-03","cited_by_count":33},{"id":"1601.01530","title":"Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling","created":"2016-01-07","cited_by_count":25},{"id":"1609.01462","title":"Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks","created":"2016-09-06","cited_by_count":19},{"id":"2305.11916","title":"F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks","created":"2023-05-21","cited_by_count":18},{"id":"2311.18550","title":"Search Still Matters: Information Retrieval in the Era of Generative AI","created":"2023-11-30","cited_by_count":17},{"id":"2510.01617","title":"AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System","created":"2025-10-02","cited_by_count":15},{"id":"2312.17522","title":"Overview of the PromptCBLUE Shared Task in CHIP2023","created":"2023-12-29","cited_by_count":14},{"id":"2301.11503","title":"Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation","created":"2023-01-27","cited_by_count":13},{"id":"2009.02070","title":"AutoTrans: Automating Transformer Design via Reinforced Architecture Search","created":"2020-09-04","cited_by_count":12},{"id":"2203.11720","title":"Continuous Detection, Rapidly React: Unseen Rumors Detection based on Continual Prompt-Tuning","created":"2022-03-16","cited_by_count":12},{"id":"2412.07619","title":"DRUM: Learning Demonstration Retriever for Large MUlti-modal Models","created":"2024-12-10","cited_by_count":10},{"id":"2009.10680","title":"AutoRC: Improving BERT Based Relation Classification Models via Architecture Search","created":"2020-09-22","cited_by_count":9},{"id":"2502.01033","title":"PARA: Parameter-Efficient Fine-tuning with Prompt Aware Representation Adjustment","created":"2025-02-03","cited_by_count":9},{"id":"2409.17834","title":"PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdification","created":"2024-09-26","cited_by_count":8},{"id":"1803.11326","title":"Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant","created":"2018-03-30","cited_by_count":7},{"id":"2510.04655","title":"FT-MDT: Extracting Decision Trees from Medical Texts via a Novel Low-rank Adaptation Method","created":"2025-10-06","cited_by_count":7},{"id":"2401.02034","title":"Text2MDT: Extracting Medical Decision Trees from Medical Texts","created":"2024-01-04","cited_by_count":6},{"id":"2601.16503","title":"MRAG: Benchmarking Retrieval-Augmented Generation for Bio-medicine","created":"2026-01-23","cited_by_count":4},{"id":"2502.13725","title":"Adapting Large Language Models for Time Series Modeling via a Novel Parameter-efficient Adaptation Method","created":"2025-02-19","cited_by_count":3},{"id":"2601.17921","title":"ShapLoRA: Allocation of Low-rank Adaption on Large Language Models via Shapley Value Inspired Importance Estimation","created":"2026-01-25","cited_by_count":3},{"id":"2101.00396","title":"Lex-BERT: Enhancing BERT based NER with lexicons","created":"2021-01-02","cited_by_count":2},{"id":"2601.21767","title":"Evaluating ChatGPT on Medical Information Extraction Tasks: Performance, Explainability and Beyond","created":"2026-01-29","cited_by_count":1},{"id":"2602.03368","title":"Pursuing Best Industrial Practices for Retrieval-Augmented Generation in the Medical Domain","created":"2026-02-03","cited_by_count":1},{"id":"2602.03563","title":"ACL: Aligned Contrastive Learning Improves BERT and Multi-exit BERT Fine-tuning","created":"2026-02-03","cited_by_count":1}],"next_cursor":null}