{"list":"other","total":64,"rows":[{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"id":"2302.14520","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","created":"2023-02-28","cited_by_count":420},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2112.07916","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","created":"2021-12-15","cited_by_count":232},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161},{"id":"1906.03741","title":"BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization","created":"2019-06-10","cited_by_count":156},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142},{"id":"2004.15011","title":"TLDR: Extreme Summarization of Scientific Documents","created":"2020-04-30","cited_by_count":136},{"id":"1905.13164","title":"Hierarchical Transformers for Multi-Document Summarization","created":"2019-05-30","cited_by_count":132},{"id":"2302.08081","title":"Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization","created":"2023-02-16","cited_by_count":122},{"id":"2012.04281","title":"CTRLsum: Towards Generic Controllable Text Summarization","created":"2020-12-08","cited_by_count":98},{"id":"1609.09552","title":"Controlling Output Length in Neural Encoder-Decoders","created":"2016-09-30","cited_by_count":75},{"id":"2005.10043","title":"Leveraging Graph to Improve Abstractive Multi-Document Summarization","created":"2020-05-20","cited_by_count":67},{"id":"2110.10150","title":"Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents","created":"2021-10-16","cited_by_count":65},{"id":"2110.08499","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","created":"2021-10-16","cited_by_count":62},{"id":"2205.11465","title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","created":"2022-05-23","cited_by_count":50},{"id":"2211.15914","title":"Prompted Opinion Summarization with GPT-3.5","created":"2022-11-29","cited_by_count":44},{"id":"1907.03491","title":"Searching for Effective Neural Extractive Summarization: What Works and What's Next","created":"2019-07-08","cited_by_count":38},{"id":"2005.01840","title":"Exploring Content Selection in Summarization of Novel Chapters","created":"2020-05-04","cited_by_count":29},{"id":"2208.09770","title":"Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization","created":"2022-08-21","cited_by_count":29},{"id":"2109.05199","title":"A Survey on Multi-modal Summarization","created":"2021-09-11","cited_by_count":26},{"id":"2205.03468","title":"The AI Index 2022 Annual Report","created":"2022-05-02","cited_by_count":19},{"id":"2006.10213","title":"SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization","created":"2020-06-18","cited_by_count":15},{"id":"2208.14585","title":"The Glass Ceiling of Automatic Evaluation in Natural Language Generation","created":"2022-08-31","cited_by_count":10},{"id":"2001.07331","title":"Length-controllable Abstractive Summarization by Guiding with Summary Prototype","created":"2020-01-21","cited_by_count":9},{"id":"2305.02483","title":"Personalized Abstractive Summarization by Tri-agent Generation Pipeline","created":"2023-05-04","cited_by_count":4}],"next_cursor":null}