{"list":"other","total":64,"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":"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":"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"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":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169},{"id":"2001.11770","title":"Break It Down: A Question Understanding Benchmark","created":"2020-01-31","cited_by_count":131},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88},{"id":"2102.03315","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","created":"2021-02-05","cited_by_count":80},{"id":"2210.01613","title":"Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering","created":"2022-10-04","cited_by_count":72},{"id":"2101.00436","title":"Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval","created":"2021-01-02","cited_by_count":63},{"id":"2110.06918","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","created":"2021-10-13","cited_by_count":60},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","cited_by_count":57},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45},{"id":"2305.14628","title":"Getting MoRE out of Mixture of Language Model Reasoning Experts","created":"2023-05-24","cited_by_count":44},{"id":"2112.03254","title":"Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention","created":"2021-12-06","cited_by_count":40},{"id":"1909.01958","title":"From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project","created":"2019-09-04","cited_by_count":33},{"id":"2003.10555","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","created":"2020-03-23","cited_by_count":27},{"id":"2210.16433","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","created":"2022-10-28","cited_by_count":24},{"id":"2210.00185","title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","created":"2022-10-01","cited_by_count":8},{"id":"2205.12496","title":"Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts","created":"2022-05-25","cited_by_count":7},{"id":"2205.03685","title":"Better Retrieval May Not Lead to Better Question Answering","created":"2022-05-07","cited_by_count":3}],"next_cursor":null}