{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2012.09852","title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning","created":"2020-12-17","cited_by_count":234},{"id":"2212.10001","title":"Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters","created":"2022-12-20","cited_by_count":222},{"id":"2203.12277","title":"Unified Structure Generation for Universal Information Extraction","created":"2022-03-23","cited_by_count":221},{"id":"2312.17617","title":"Large Language Models for Generative Information Extraction: A Survey","created":"2023-12-29","cited_by_count":185},{"id":"2101.05779","title":"Structured Prediction as Translation between Augmented Natural Languages","created":"2021-01-14","cited_by_count":183},{"id":"2304.08085","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","created":"2023-04-17","cited_by_count":170},{"id":"2304.10428","title":"GPT-NER: Named Entity Recognition via Large Language Models","created":"2023-04-20","cited_by_count":160},{"id":"2310.03668","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","created":"2023-10-05","cited_by_count":119},{"id":"2012.04373","title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","created":"2020-12-08","cited_by_count":104},{"id":"2112.10070","title":"Unified Named Entity Recognition as Word-Word Relation Classification","created":"2021-12-19","cited_by_count":90},{"id":"2311.08526","title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","created":"2023-11-14","cited_by_count":88},{"id":"2305.14201","title":"Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks","created":"2023-05-23","cited_by_count":84},{"id":"1805.02023","title":"Chinese NER Using Lattice LSTM","created":"2018-05-05","cited_by_count":81},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"2308.03279","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","created":"2023-08-07","cited_by_count":72},{"id":"2304.04487","title":"Inference with Reference: Lossless Acceleration of Large Language Models","created":"2023-04-10","cited_by_count":65},{"id":"2310.10035","title":"Empirical Study of Zero-Shot NER with ChatGPT","created":"2023-10-16","cited_by_count":60},{"id":"2205.10475","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","created":"2022-05-21","cited_by_count":45},{"id":"2306.01128","title":"Learning Transformer Programs","created":"2023-06-01","cited_by_count":41},{"id":"2305.15444","title":"PromptNER: Prompting For Named Entity Recognition","created":"2023-05-24","cited_by_count":35},{"id":"2105.07148","title":"Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter","created":"2021-05-15","cited_by_count":34},{"id":"2203.12918","title":"A Rationale-Centric Framework for Human-in-the-loop Machine Learning","created":"2022-03-24","cited_by_count":27},{"id":"2307.06962","title":"Copy Is All You Need","created":"2023-07-13","cited_by_count":27},{"id":"2208.14565","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","created":"2022-08-30","cited_by_count":24},{"id":"1908.05969","title":"Simplify the Usage of Lexicon in Chinese NER","created":"2019-08-16","cited_by_count":23},{"id":"2209.15206","title":"What Makes Pre-trained Language Models Better Zero-shot Learners?","created":"2022-09-30","cited_by_count":23},{"id":"2311.03748","title":"Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning","created":"2023-11-07","cited_by_count":21},{"id":"2208.12995","title":"Domain-Specific NER via Retrieving Correlated Samples","created":"2022-08-27","cited_by_count":11},{"id":"2305.17903","title":"Deeply Coupled Cross-Modal Prompt Learning","created":"2023-05-29","cited_by_count":11},{"id":"2211.14838","title":"PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets","created":"2022-11-27","cited_by_count":10},{"id":"2311.07306","title":"What Large Language Models Bring to Text-rich VQA?","created":"2023-11-13","cited_by_count":10},{"id":"2305.11038","title":"Learning In-context Learning for Named Entity Recognition","created":"2023-05-18","cited_by_count":7}],"next_cursor":null}