{"list":"other","total":86,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"1508.01991","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","created":"2015-08-09","cited_by_count":546},{"id":"1905.07129","title":"ERNIE: Enhanced Language Representation with Informative Entities","created":"2019-05-17","cited_by_count":528},{"id":"1908.09203","title":"Release Strategies and the Social Impacts of Language Models","created":"2019-08-24","cited_by_count":513},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"1603.01354","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","created":"2016-03-04","cited_by_count":341},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316},{"id":"1707.06875","title":"Why We Need New Evaluation Metrics for NLG","created":"2017-07-21","cited_by_count":233},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"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":"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":"2004.03329","title":"MedDialog: Two Large-scale Medical Dialogue Datasets","created":"2020-04-07","cited_by_count":161},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158},{"id":"2011.02593","title":"Detecting Hallucinated Content in Conditional Neural Sequence Generation","created":"2020-11-05","cited_by_count":152},{"id":"1605.05101","title":"Recurrent Neural Network for Text Classification with Multi-Task Learning","created":"2016-05-17","cited_by_count":144},{"id":"1805.08298","title":"Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation","created":"2018-05-21","cited_by_count":141},{"id":"2004.08449","title":"Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills","created":"2020-04-17","cited_by_count":131},{"id":"2304.01097","title":"DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task","created":"2023-04-03","cited_by_count":131},{"id":"2303.11032","title":"DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4","created":"2023-03-20","cited_by_count":130},{"id":"2308.03549","title":"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue","created":"2023-08-07","cited_by_count":119},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115},{"id":"2005.03954","title":"Towards Conversational Recommendation over Multi-Type Dialogs","created":"2020-05-08","cited_by_count":107},{"id":"2106.08087","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","created":"2021-06-15","cited_by_count":101},{"id":"2311.09774","title":"HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs","created":"2023-11-16","cited_by_count":92},{"id":"2308.14346","title":"DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation","created":"2023-08-28","cited_by_count":90},{"id":"2010.05873","title":"Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data","created":"2020-10-12","cited_by_count":84},{"id":"1805.02023","title":"Chinese NER Using Lattice LSTM","created":"2018-05-05","cited_by_count":81},{"id":"2003.07490","title":"Recent Advances and Challenges in Task-oriented Dialog System","created":"2020-03-17","cited_by_count":78},{"id":"1812.09471","title":"Joint Slot Filling and Intent Detection via Capsule Neural Networks","created":"2018-12-22","cited_by_count":73},{"id":"1901.10623","title":"End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis","created":"2019-01-30","cited_by_count":70},{"id":"2004.11795","title":"FLAT: Chinese NER Using Flat-Lattice Transformer","created":"2020-04-24","cited_by_count":67},{"id":"2310.15896","title":"BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPT","created":"2023-10-24","cited_by_count":65},{"id":"1804.06512","title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems","created":"2018-04-18","cited_by_count":53},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53},{"id":"1505.08075","title":"Transition-Based Dependency Parsing with Stack Long Short-Term Memory","created":"2015-05-29","cited_by_count":45},{"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":"2204.08997","title":"A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets","created":"2022-04-19","cited_by_count":45},{"id":"2105.07148","title":"Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter","created":"2021-05-15","cited_by_count":34},{"id":"2311.02216","title":"Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data","created":"2023-11-03","cited_by_count":33},{"id":"2105.06071","title":"Semi-Supervised Variational Reasoning for Medical Dialogue Generation","created":"2021-05-13","cited_by_count":30},{"id":"2012.11988","title":"Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation","created":"2020-12-22","cited_by_count":24},{"id":"1906.02239","title":"Extracting Symptoms and their Status from Clinical Conversations","created":"2019-06-05","cited_by_count":23},{"id":"2311.16789","title":"A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Models","created":"2023-11-28","cited_by_count":23},{"id":"1812.06081","title":"A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization","created":"2018-12-14","cited_by_count":20},{"id":"2201.07745","title":"Improving Biomedical Information Retrieval with Neural Retrievers","created":"2022-01-19","cited_by_count":20},{"id":"2106.06471","title":"Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation","created":"2021-05-25","cited_by_count":19},{"id":"2308.11578","title":"Refashioning Emotion Recognition Modelling: The Advent of Generalised Large Models","created":"2023-08-21","cited_by_count":16},{"id":"1812.02793","title":"Generation of Synthetic Electronic Medical Record Text","created":"2018-12-06","cited_by_count":14},{"id":"2308.07635","title":"LLM-Mini-CEX: Automatic Evaluation of Large Language Model for Diagnostic Conversation","created":"2023-08-15","cited_by_count":14},{"id":"2306.02923","title":"MidMed: Towards Mixed-Type Dialogues for Medical Consultation","created":"2023-06-05","cited_by_count":13},{"id":"2005.05442","title":"On the Generation of Medical Dialogues for COVID-19","created":"2020-05-11","cited_by_count":12},{"id":"2204.13953","title":"\"My nose is running.\"\"Are you also coughing?\": Building A Medical Diagnosis Agent with Interpretable Inquiry Logics","created":"2022-04-29","cited_by_count":9},{"id":"2206.08611","title":"Medical Dialogue Response Generation with Pivotal Information Recalling","created":"2022-06-17","cited_by_count":9},{"id":"2104.07874","title":"Translational NLP: A New Paradigm and General Principles for Natural Language Processing Research","created":"2021-04-16","cited_by_count":7},{"id":"1907.07972","title":"Deep Neural Models for Medical Concept Normalization in User-Generated Texts","created":"2019-07-18","cited_by_count":5},{"id":"2212.02000","title":"Wish I Can Feel What You Feel: A Neural Approach for Empathetic Response Generation","created":"2022-12-05","cited_by_count":5},{"id":"2305.16833","title":"KNSE: A Knowledge-aware Natural Language Inference Framework for Dialogue Symptom Status Recognition","created":"2023-05-26","cited_by_count":5},{"id":"2009.11247","title":"Novel Computational Linguistic Measures, Dialogue System and the Development of SOPHIE: Standardized Online Patient for Healthcare Interaction Education","created":"2020-09-23","cited_by_count":4},{"id":"2110.00159","title":"Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning","created":"2021-10-01","cited_by_count":3}],"next_cursor":null}