{"list":"other","total":56,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2202.01279","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","created":"2022-02-02","cited_by_count":289},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"2012.04584","title":"Distilling Knowledge from Reader to Retriever for Question Answering","created":"2020-12-08","cited_by_count":226},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220},{"id":"2110.08387","title":"Generated Knowledge Prompting for Commonsense Reasoning","created":"2021-10-15","cited_by_count":214},{"id":"1912.13283","title":"oLMpics -- On what Language Model Pre-training Captures","created":"2019-12-31","cited_by_count":161},{"id":"2004.05483","title":"Unsupervised Commonsense Question Answering with Self-Talk","created":"2020-04-11","cited_by_count":161},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"1902.01718","title":"End-to-End Open-Domain Question Answering with BERTserini","created":"2019-02-05","cited_by_count":152},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2008.02637","title":"Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets","created":"2020-08-06","cited_by_count":138},{"id":"2203.05115","title":"Internet-augmented language models through few-shot prompting for open-domain question answering","created":"2022-03-10","cited_by_count":131},{"id":"2204.10628","title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","created":"2022-04-22","cited_by_count":113},{"id":"2206.02743","title":"A Neural Corpus Indexer for Document Retrieval","created":"2022-06-06","cited_by_count":111},{"id":"2207.00747","title":"Rationale-Augmented Ensembles in Language Models","created":"2022-07-02","cited_by_count":111},{"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":"2206.10128","title":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation","created":"2022-06-21","cited_by_count":48},{"id":"2006.07490","title":"Understanding Unintended Memorization in Federated Learning","created":"2020-06-12","cited_by_count":36},{"id":"2208.09257","title":"Ultron: An Ultimate Retriever on Corpus with a Model-based Indexer","created":"2022-08-19","cited_by_count":31},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29},{"id":"1609.08824","title":"Equation Parsing: Mapping Sentences to Grounded Equations","created":"2016-09-28","cited_by_count":9}],"next_cursor":null}