{"list":"other","total":54,"rows":[{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"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":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"id":"2308.08241","title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","created":"2023-08-16","cited_by_count":169},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"2310.03589","title":"TimeGPT-1","created":"2023-10-05","cited_by_count":158},{"id":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144},{"id":"2304.07619","title":"Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models","created":"2023-04-15","cited_by_count":129},{"id":"2308.08469","title":"LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters","created":"2023-08-16","cited_by_count":129},{"id":"2305.15525","title":"Large Language Models are Few-Shot Health Learners","created":"2023-05-24","cited_by_count":118},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110},{"id":"2308.15197","title":"Where Would I Go Next? Large Language Models as Human Mobility Predictors","created":"2023-08-29","cited_by_count":93},{"id":"2304.06798","title":"On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence","created":"2023-04-13","cited_by_count":88},{"id":"2401.10134","title":"Spatial-Temporal Large Language Model for Traffic Prediction","created":"2024-01-18","cited_by_count":83},{"id":"2306.11025","title":"Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting","created":"2023-06-19","cited_by_count":77},{"id":"2303.12311","title":"Frozen Language Model Helps ECG Zero-Shot Learning","created":"2023-03-22","cited_by_count":62},{"id":"2304.05351","title":"The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challenges","created":"2023-04-10","cited_by_count":59},{"id":"2306.12659","title":"Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models","created":"2023-06-22","cited_by_count":58},{"id":"2210.01753","title":"HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences","created":"2022-10-04","cited_by_count":57},{"id":"2305.10716","title":"A Survey on Time-Series Pre-Trained Models","created":"2023-05-18","cited_by_count":52},{"id":"2209.05479","title":"Leveraging Language Foundation Models for Human Mobility Forecasting","created":"2022-09-11","cited_by_count":50},{"id":"2305.16646","title":"Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning","created":"2023-05-26","cited_by_count":45},{"id":"2306.03763","title":"ChatGPT Informed Graph Neural Network for Stock Movement Prediction","created":"2023-05-28","cited_by_count":41},{"id":"2311.14332","title":"GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputation","created":"2023-11-24","cited_by_count":35},{"id":"2309.06236","title":"The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models","created":"2023-09-12","cited_by_count":34},{"id":"2206.02353","title":"Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data","created":"2022-06-06","cited_by_count":27},{"id":"2305.12398","title":"Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition","created":"2023-05-21","cited_by_count":27},{"id":"2308.05361","title":"WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine","created":"2023-08-10","cited_by_count":17},{"id":"2305.14847","title":"Drafting Event Schemas using Language Models","created":"2023-05-24","cited_by_count":6}],"next_cursor":null}