{"list":"other","total":53,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"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":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"id":"1909.05855","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","created":"2019-09-12","cited_by_count":434},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"2306.06031","title":"FinGPT: Open-Source Financial Large Language Models","created":"2023-06-09","cited_by_count":253},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"1912.07840","title":"Cross-Lingual Ability of Multilingual BERT: An Empirical Study","created":"2019-12-17","cited_by_count":182},{"id":"2306.16092","title":"Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture","created":"2023-06-28","cited_by_count":122},{"id":"2004.14444","title":"The Effect of Natural Distribution Shift on Question Answering Models","created":"2020-04-29","cited_by_count":104},{"id":"1911.03681","title":"E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT","created":"2019-11-09","cited_by_count":96},{"id":"2305.12002","title":"XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters","created":"2023-05-19","cited_by_count":92},{"id":"2105.03654","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","created":"2021-05-08","cited_by_count":76},{"id":"2305.15062","title":"Lawyer LLaMA Technical Report","created":"2023-05-24","cited_by_count":54},{"id":"2307.09007","title":"On the (In)Effectiveness of Large Language Models for Chinese Text Correction","created":"2023-07-18","cited_by_count":54},{"id":"1911.09969","title":"The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service","created":"2019-11-22","cited_by_count":47},{"id":"2009.07162","title":"Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product","created":"2020-09-15","cited_by_count":39},{"id":"2203.03367","title":"Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval","created":"2022-03-07","cited_by_count":27},{"id":"2204.07789","title":"Contrastive Learning with Hard Negative Entities for Entity Set Expansion","created":"2022-04-16","cited_by_count":26},{"id":"2009.02835","title":"E-BERT: A Phrase and Product Knowledge Enhanced Language Model for E-commerce","created":"2020-09-07","cited_by_count":19},{"id":"2105.00388","title":"Billion-scale Pre-trained E-commerce Product Knowledge Graph Model","created":"2021-05-02","cited_by_count":13},{"id":"2104.06960","title":"K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce","created":"2021-04-14","cited_by_count":12},{"id":"2211.10997","title":"Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge","created":"2022-11-20","cited_by_count":12},{"id":"2208.06150","title":"Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search","created":"2022-08-12","cited_by_count":10},{"id":"2012.07553","title":"An End-to-End Solution for Named Entity Recognition in eCommerce Search","created":"2020-12-11","cited_by_count":6},{"id":"2005.13783","title":"JointMap: Joint Query Intent Understanding For Modeling Intent Hierarchies in E-commerce Search","created":"2020-05-28","cited_by_count":5},{"id":"2210.03915","title":"Short Text Pre-training with Extended Token Classification for E-commerce Query Understanding","created":"2022-10-08","cited_by_count":5},{"id":"2005.11075","title":"Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning","created":"2020-05-22","cited_by_count":4}],"next_cursor":null}