{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333},{"id":"1909.00161","title":"Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach","created":"2019-08-31","cited_by_count":308},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2202.01279","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","created":"2022-02-02","cited_by_count":289},{"id":"1605.07723","title":"Data Programming: Creating Large Training Sets, Quickly","created":"2016-05-25","cited_by_count":246},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2010.09535","title":"Cold-start Active Learning through Self-supervised Language Modeling","created":"2020-10-19","cited_by_count":128},{"id":"1707.05928","title":"Deep Active Learning for Named Entity Recognition","created":"2017-07-19","cited_by_count":108},{"id":"1810.02840","title":"Training Complex Models with Multi-Task Weak Supervision","created":"2018-10-05","cited_by_count":106},{"id":"2002.11955","title":"Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods","created":"2020-02-27","cited_by_count":98},{"id":"2103.11955","title":"Improving and Simplifying Pattern Exploiting Training","created":"2021-03-22","cited_by_count":97},{"id":"2109.11377","title":"WRENCH: A Comprehensive Benchmark for Weak Supervision","created":"2021-09-23","cited_by_count":96},{"id":"1606.05464","title":"Stance Detection with Bidirectional Conditional Encoding","created":"2016-06-17","cited_by_count":93},{"id":"1809.08370","title":"Semi-Supervised Sequence Modeling with Cross-View Training","created":"2018-09-22","cited_by_count":75},{"id":"2202.05433","title":"A Survey on Programmatic Weak Supervision","created":"2022-02-11","cited_by_count":66},{"id":"2004.06025","title":"Learning from Rules Generalizing Labeled Exemplars","created":"2020-04-13","cited_by_count":59},{"id":"1812.00417","title":"Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale","created":"2018-12-02","cited_by_count":52},{"id":"2012.06046","title":"Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling","created":"2020-12-11","cited_by_count":52},{"id":"2104.05514","title":"Self-Training with Weak Supervision","created":"2021-04-12","cited_by_count":49},{"id":"2210.10109","title":"A Survey of Active Learning for Natural Language Processing","created":"2022-10-18","cited_by_count":40},{"id":"1804.09530","title":"Strong Baselines for Neural Semi-supervised Learning under Domain Shift","created":"2018-04-25","cited_by_count":39},{"id":"2210.17541","title":"Zero-Shot Text Classification with Self-Training","created":"2022-10-31","cited_by_count":26},{"id":"1510.02847","title":"Active Learning from Weak and Strong Labelers","created":"2015-10-09","cited_by_count":22},{"id":"2005.12801","title":"Active Imitation Learning with Noisy Guidance","created":"2020-05-26","cited_by_count":15},{"id":"2203.09735","title":"PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning","created":"2022-03-18","cited_by_count":14},{"id":"1909.00415","title":"Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training","created":"2019-09-01","cited_by_count":10},{"id":"2203.01382","title":"Nemo: Guiding and Contextualizing Weak Supervision for Interactive Data Programming","created":"2022-03-02","cited_by_count":10},{"id":"1907.11184","title":"HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop","created":"2019-07-25","cited_by_count":7},{"id":"2104.03958","title":"GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns","created":"2021-04-08","cited_by_count":6}],"next_cursor":null}