{"list":"other","total":57,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"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":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333},{"id":"2306.04637","title":"Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection","created":"2023-06-07","cited_by_count":298},{"id":"1908.08351","title":"Compositionality decomposed: how do neural networks generalise?","created":"2019-08-22","cited_by_count":265},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197},{"id":"2211.04486","title":"Active Example Selection for In-Context Learning","created":"2022-11-08","cited_by_count":196},{"id":"2302.12246","title":"Active Prompting with Chain-of-Thought for Large Language Models","created":"2023-02-23","cited_by_count":154},{"id":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"2010.09535","title":"Cold-start Active Learning through Self-supervised Language Modeling","created":"2020-10-19","cited_by_count":128},{"id":"2107.14263","title":"Batch Active Learning at Scale","created":"2021-07-29","cited_by_count":127},{"id":"2305.01115","title":"In-Context Learning Unlocked for Diffusion Models","created":"2023-05-01","cited_by_count":104},{"id":"2311.01459","title":"Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization","created":"2023-11-02","cited_by_count":101},{"id":"2203.13450","title":"A Comparative Survey of Deep Active Learning","created":"2022-03-25","cited_by_count":89},{"id":"2106.09675","title":"Gone Fishing: Neural Active Learning with Fisher Embeddings","created":"2021-06-17","cited_by_count":88},{"id":"1711.00941","title":"Deep Active Learning over the Long Tail","created":"2017-11-02","cited_by_count":84},{"id":"2311.00288","title":"Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks","created":"2023-11-01","cited_by_count":55},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54},{"id":"2201.11206","title":"Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes","created":"2022-01-26","cited_by_count":49},{"id":"2105.13017","title":"Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits","created":"2021-05-27","cited_by_count":32},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30},{"id":"2305.18787","title":"Universality and Limitations of Prompt Tuning","created":"2023-05-30","cited_by_count":30},{"id":"1506.02348","title":"Convergence Rates of Active Learning for Maximum Likelihood Estimation","created":"2015-06-08","cited_by_count":25},{"id":"2401.06692","title":"An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models","created":"2024-01-12","cited_by_count":23},{"id":"2106.04763","title":"Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2021-06-09","cited_by_count":22},{"id":"2305.16617","title":"Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model","created":"2023-05-26","cited_by_count":18},{"id":"2111.01768","title":"Nearly Optimal Algorithms for Level Set Estimation","created":"2021-11-02","cited_by_count":17},{"id":"2302.07994","title":"\\`A-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting","created":"2023-02-15","cited_by_count":17},{"id":"2105.06499","title":"Improved Algorithms for Agnostic Pool-based Active Classification","created":"2021-05-13","cited_by_count":15},{"id":"2012.08073","title":"Chernoff Sampling for Active Testing and Extension to Active Regression","created":"2020-12-15","cited_by_count":13},{"id":"2306.00310","title":"Prompt Algebra for Task Composition","created":"2023-06-01","cited_by_count":6},{"id":"2306.07549","title":"Fixed-Budget Best-Arm Identification with Heterogeneous Reward Variances","created":"2023-06-13","cited_by_count":6},{"id":"2111.09785","title":"DIVA: Dataset Derivative of a Learning Task","created":"2021-11-18","cited_by_count":5},{"id":"2305.15040","title":"Active Learning for Natural Language Generation","created":"2023-05-24","cited_by_count":3},{"id":"2306.08942","title":"Active Representation Learning for General Task Space with Applications in Robotics","created":"2023-06-15","cited_by_count":2}],"next_cursor":null}