{"list":"other","total":52,"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"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":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"2010.00710","title":"Nearest Neighbor Machine Translation","created":"2020-10-01","cited_by_count":209},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158},{"id":"1906.02448","title":"Bridging the Gap between Training and Inference for Neural Machine Translation","created":"2019-06-06","cited_by_count":123},{"id":"2402.06925","title":"A Thorough Examination of Decoding Methods in the Era of LLMs","created":"2024-02-10","cited_by_count":114},{"id":"2205.12674","title":"Training Language Models with Memory Augmentation","created":"2022-05-25","cited_by_count":113},{"id":"1405.5869","title":"Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)","created":"2014-05-22","cited_by_count":109},{"id":"1602.07776","title":"Recurrent Neural Network Grammars","created":"2016-02-25","cited_by_count":109},{"id":"2012.12624","title":"Learning Dense Representations of Phrases at Scale","created":"2020-12-23","cited_by_count":91},{"id":"2102.02557","title":"Adaptive Semiparametric Language Models","created":"2021-02-04","cited_by_count":83},{"id":"1808.04776","title":"Retrieve and Refine: Improved Sequence Generation Models For Dialogue","created":"2018-08-14","cited_by_count":82},{"id":"1909.04849","title":"A Discrete Hard EM Approach for Weakly Supervised Question Answering","created":"2019-09-11","cited_by_count":78},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75},{"id":"1812.01194","title":"A Retrieve-and-Edit Framework for Predicting Structured Outputs","created":"2018-12-04","cited_by_count":73},{"id":"1906.05807","title":"Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index","created":"2019-06-13","cited_by_count":64},{"id":"2105.11269","title":"Neural Machine Translation with Monolingual Translation Memory","created":"2021-05-24","cited_by_count":61},{"id":"2210.14140","title":"Contrastive Search Is What You Need For Neural Text Generation","created":"2022-10-25","cited_by_count":59},{"id":"1902.02192","title":"Non-Monotonic Sequential Text Generation","created":"2019-02-05","cited_by_count":55},{"id":"2303.09867","title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","created":"2023-03-17","cited_by_count":52},{"id":"1809.05296","title":"Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory","created":"2018-09-14","cited_by_count":49},{"id":"1806.07042","title":"Response Generation by Context-aware Prototype Editing","created":"2018-06-19","cited_by_count":40},{"id":"2212.01349","title":"Nonparametric Masked Language Modeling","created":"2022-12-02","cited_by_count":40},{"id":"2109.08133","title":"Phrase Retrieval Learns Passage Retrieval, Too","created":"2021-09-16","cited_by_count":33},{"id":"1509.01469","title":"Quantization based Fast Inner Product Search","created":"2015-09-04","cited_by_count":29},{"id":"2307.06962","title":"Copy Is All You Need","created":"2023-07-13","cited_by_count":27},{"id":"2312.02428","title":"FreestyleRet: Retrieving Images from Style-Diversified Queries","created":"2023-12-05","cited_by_count":20},{"id":"2305.14625","title":"KNN-LM Does Not Improve Open-ended Text Generation","created":"2023-05-24","cited_by_count":10},{"id":"2302.11799","title":"FiTs: Fine-grained Two-stage Training for Knowledge-aware Question Answering","created":"2023-02-23","cited_by_count":8},{"id":"2306.11485","title":"Explicit Syntactic Guidance for Neural Text Generation","created":"2023-06-20","cited_by_count":8}],"next_cursor":null}