{"list":"other","total":67,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"1804.11283","title":"Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies","created":"2018-04-30","cited_by_count":294},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2103.06268","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","created":"2021-03-10","cited_by_count":236},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148},{"id":"2310.00785","title":"BooookScore: A systematic exploration of book-length summarization in the era of LLMs","created":"2023-10-01","cited_by_count":137},{"id":"2004.12158","title":"How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence","created":"2020-04-25","cited_by_count":129},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128},{"id":"1910.00523","title":"BillSum: A Corpus for Automatic Summarization of US Legislation","created":"2019-10-01","cited_by_count":117},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113},{"id":"1906.02192","title":"Large-Scale Multi-Label Text Classification on EU Legislation","created":"2019-06-05","cited_by_count":104},{"id":"2109.00904","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","created":"2021-09-02","cited_by_count":90},{"id":"1805.01217","title":"CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service","created":"2018-05-03","cited_by_count":73},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71},{"id":"2301.13126","title":"LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain","created":"2023-01-30","cited_by_count":68},{"id":"1911.00841","title":"Question Answering for Privacy Policies: Combining Computational and Legal Perspectives","created":"2019-11-03","cited_by_count":67},{"id":"2306.02069","title":"MultiLegalPile: A 689GB Multilingual Legal Corpus","created":"2023-06-03","cited_by_count":60},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57},{"id":"2305.07507","title":"LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development","created":"2023-05-12","cited_by_count":54},{"id":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49},{"id":"2011.11928","title":"GLGE: A New General Language Generation Evaluation Benchmark","created":"2020-11-24","cited_by_count":47},{"id":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44},{"id":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","cited_by_count":42},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40},{"id":"2210.13448","title":"EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain","created":"2022-10-24","cited_by_count":40},{"id":"2209.06049","title":"Pre-trained Language Models for the Legal Domain: A Case Study on Indian Law","created":"2022-09-13","cited_by_count":39},{"id":"2302.12039","title":"Natural Language Processing in the Legal Domain","created":"2023-02-23","cited_by_count":38},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36},{"id":"2209.01650","title":"ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining","created":"2022-09-04","cited_by_count":25},{"id":"2108.12960","title":"LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation","created":"2021-08-30","cited_by_count":24},{"id":"2106.15876","title":"Incorporating Domain Knowledge for Extractive Summarization of Legal Case Documents","created":"2021-06-30","cited_by_count":23},{"id":"2305.05627","title":"An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text","created":"2023-05-09","cited_by_count":23},{"id":"2108.07140","title":"MTG: A Benchmark Suite for Multilingual Text Generation","created":"2021-08-13","cited_by_count":22},{"id":"2305.14989","title":"Dolphin: A Challenging and Diverse Benchmark for Arabic NLG","created":"2023-05-24","cited_by_count":22},{"id":"2310.14088","title":"MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation","created":"2023-10-21","cited_by_count":19},{"id":"2101.11284","title":"Measuring Law Over Time: A Network Analytical Framework with an Application to Statutes and Regulations in the United States and Germany","created":"2021-01-27","cited_by_count":17},{"id":"2112.13610","title":"CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark","created":"2021-12-27","cited_by_count":16},{"id":"2110.01485","title":"JuriBERT: A Masked-Language Model Adaptation for French Legal Text","created":"2021-10-04","cited_by_count":14},{"id":"2110.12201","title":"Spanish Legalese Language Model and Corpora","created":"2021-10-23","cited_by_count":11},{"id":"2405.14211","title":"ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks","created":"2024-05-23","cited_by_count":11},{"id":"2210.12437","title":"Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance","created":"2022-10-22","cited_by_count":9},{"id":"2306.00672","title":"Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking","created":"2023-06-01","cited_by_count":9},{"id":"2404.00594","title":"LexAbSumm: Aspect-based Summarization of Legal Decisions","created":"2024-03-31","cited_by_count":9},{"id":"2403.19317","title":"Beyond Borders: Investigating Cross-Jurisdiction Transfer in Legal Case Summarization","created":"2024-03-28","cited_by_count":8},{"id":"2210.08284","title":"AraLegal-BERT: A pretrained language model for Arabic Legal text","created":"2022-10-15","cited_by_count":7},{"id":"2212.09825","title":"What to Read in a Contract? Party-Specific Summarization of Legal Obligations, Entitlements, and Prohibitions","created":"2022-12-19","cited_by_count":5},{"id":"2307.05081","title":"Argumentative Segmentation Enhancement for Legal Summarization","created":"2023-07-11","cited_by_count":4},{"id":"2404.00595","title":"Query-driven Relevant Paragraph Extraction from Legal Judgments","created":"2024-03-31","cited_by_count":4}],"next_cursor":null}