{"list":"other","total":55,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"1905.05583","title":"How to Fine-Tune BERT for Text Classification?","created":"2019-05-14","cited_by_count":411},{"id":"1807.05118","title":"Tune: A Research Platform for Distributed Model Selection and Training","created":"2018-07-13","cited_by_count":395},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2205.07246","title":"FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning","created":"2022-05-15","cited_by_count":232},{"id":"2302.10198","title":"Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT","created":"2023-02-19","cited_by_count":155},{"id":"2301.10921","title":"SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning","created":"2023-01-26","cited_by_count":133},{"id":"2006.05278","title":"An Overview of Deep Semi-Supervised Learning","created":"2020-06-09","cited_by_count":121},{"id":"2003.05689","title":"Hyper-Parameter Optimization: A Review of Algorithms and Applications","created":"2020-03-12","cited_by_count":114},{"id":"2304.03208","title":"Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster","created":"2023-04-06","cited_by_count":109},{"id":"1912.02047","title":"Neural Machine Translation: A Review and Survey","created":"2019-12-04","cited_by_count":100},{"id":"2208.07204","title":"USB: A Unified Semi-supervised Learning Benchmark for Classification","created":"2022-08-12","cited_by_count":95},{"id":"2303.14742","title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases","created":"2023-03-26","cited_by_count":86},{"id":"2305.13412","title":"Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method","created":"2023-05-22","cited_by_count":76},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75},{"id":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72},{"id":"2106.01561","title":"Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?","created":"2021-06-03","cited_by_count":62},{"id":"1906.00363","title":"Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation","created":"2019-06-02","cited_by_count":43},{"id":"2303.04673","title":"Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference","created":"2023-03-08","cited_by_count":40},{"id":"2304.01457","title":"Exploring Vision-Language Models for Imbalanced Learning","created":"2023-04-04","cited_by_count":35},{"id":"2305.12421","title":"Evaluating Open-QA Evaluation","created":"2023-05-21","cited_by_count":35},{"id":"2106.15231","title":"Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis","created":"2021-06-29","cited_by_count":30},{"id":"2203.12918","title":"A Rationale-Centric Framework for Human-in-the-loop Machine Learning","created":"2022-03-24","cited_by_count":27},{"id":"2103.09710","title":"The Human Evaluation Datasheet 1.0: A Template for Recording Details of Human Evaluation Experiments in NLP","created":"2021-03-17","cited_by_count":19},{"id":"2112.07225","title":"Margin Calibration for Long-Tailed Visual Recognition","created":"2021-12-14","cited_by_count":17},{"id":"2105.14980","title":"Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition","created":"2021-05-31","cited_by_count":13},{"id":"2204.10714","title":"Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing Annotations","created":"2022-04-22","cited_by_count":9},{"id":"2305.17041","title":"RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering","created":"2023-05-26","cited_by_count":4},{"id":"2208.08280","title":"Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction","created":"2022-08-17","cited_by_count":2}],"next_cursor":null}