{"total":97,"rows":[{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310,"area":null},{"id":"2103.06268","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","created":"2021-03-10","cited_by_count":236,"area":null},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128,"area":null},{"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,"area":null},{"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,"area":null},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40,"area":null},{"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,"area":null},{"id":"2403.17661","title":"Language Models for Text Classification: Is In-Context Learning Enough?","created":"2024-03-26","cited_by_count":40,"area":null},{"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,"area":null},{"id":"2203.11258","title":"Efficient Classification of Long Documents Using Transformers","created":"2022-03-21","cited_by_count":30,"area":null},{"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,"area":null},{"id":"2105.07903","title":"Factoring Statutory Reasoning as Language Understanding Challenges","created":"2021-05-17","cited_by_count":20,"area":null},{"id":"2211.00974","title":"Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer","created":"2022-11-02","cited_by_count":20,"area":null},{"id":"2506.01732","title":"Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training","created":"2025-06-02","cited_by_count":20,"area":null},{"id":"2109.15298","title":"Multi-granular Legal Topic Classification on Greek Legislation","created":"2021-09-30","cited_by_count":15,"area":null},{"id":"2112.08652","title":"Extreme Zero-Shot Learning for Extreme Text Classification","created":"2021-12-16","cited_by_count":15,"area":null},{"id":"2307.03539","title":"Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matchers","created":"2023-07-07","cited_by_count":15,"area":null},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2101.10726","title":"Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations","created":"2021-01-26","cited_by_count":13,"area":null},{"id":"2112.06370","title":"Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer","created":"2021-12-13","cited_by_count":13,"area":null},{"id":"2204.14081","title":"Few-shot learning for medical text: A systematic review","created":"2022-04-21","cited_by_count":13,"area":null},{"id":"2205.05812","title":"Open Vocabulary Extreme Classification Using Generative Models","created":"2022-05-12","cited_by_count":13,"area":null},{"id":"2107.02126","title":"A Survey on Deep Learning Event Extraction: Approaches and Applications","created":"2021-07-05","cited_by_count":12,"area":null},{"id":"2306.06843","title":"Recurrent Attention Networks for Long-text Modeling","created":"2023-06-12","cited_by_count":12,"area":null},{"id":"2202.05932","title":"Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification","created":"2022-02-11","cited_by_count":10,"area":null},{"id":"2404.02127","title":"LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain","created":"2024-04-02","cited_by_count":10,"area":null},{"id":"2503.12294","title":"The Lucie-7B LLM and the Lucie Training Dataset: Open resources for multilingual language generation","created":"2025-03-15","cited_by_count":10,"area":null},{"id":"2104.01666","title":"Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning","created":"2021-04-04","cited_by_count":9,"area":null},{"id":"2109.04853","title":"CoPHE: A Count-Preserving Hierarchical Evaluation Metric in Large-Scale Multi-Label Text Classification","created":"2021-09-10","cited_by_count":9,"area":null},{"id":"2506.00643","title":"SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions","created":"2025-05-31","cited_by_count":9,"area":null},{"id":"2109.07319","title":"InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2410.09527","title":"LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English","created":"2024-10-12","cited_by_count":8,"area":null},{"id":"2110.08426","title":"EncT5: A Framework for Fine-tuning T5 as Non-autoregressive Models","created":"2021-10-16","cited_by_count":7,"area":null},{"id":"2210.03968","title":"A Survey on Extreme Multi-label Learning","created":"2022-10-08","cited_by_count":7,"area":null},{"id":"2108.01139","title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors","created":"2021-08-02","cited_by_count":6,"area":null},{"id":"2109.06862","title":"Legal Transformer Models May Not Always Help","created":"2021-09-14","cited_by_count":6,"area":null},{"id":"2111.11104","title":"Hierarchical Text Classification As Sub-Hierarchy Sequence Generation","created":"2021-11-22","cited_by_count":6,"area":null},{"id":"2301.11309","title":"SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2310.20558","title":"Breaking the Token Barrier: Chunking and Convolution for Efficient Long Text Classification with BERT","created":"2023-10-31","cited_by_count":6,"area":null},{"id":"2311.09649","title":"ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2408.08981","title":"From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning","created":"2024-08-16","cited_by_count":5,"area":null},{"id":"2107.08128","title":"The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2109.00993","title":"LegaLMFiT: Efficient Short Legal Text Classification with LSTM Language Model Pre-Training","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2208.12401","title":"Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation","created":"2022-08-26","cited_by_count":4,"area":null},{"id":"2302.01842","title":"A Case Study for Compliance as Code with Graphs and Language Models: Public release of the Regulatory Knowledge Graph","created":"2023-02-03","cited_by_count":4,"area":null},{"id":"2306.14003","title":"Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers","created":"2023-06-24","cited_by_count":4,"area":null},{"id":"2408.09777","title":"Summarizing long regulatory documents with a multi-step pipeline","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2305.08655","title":"Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2308.13139","title":"MatchXML: An Efficient Text-label Matching Framework for Extreme Multi-label Text Classification","created":"2023-08-25","cited_by_count":3,"area":null},{"id":"2402.19170","title":"Improving Legal Judgement Prediction in Romanian with Long Text Encoders","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2103.00899","title":"Computationally Efficient Wasserstein Loss for Structured Labels","created":"2021-03-01","cited_by_count":2,"area":null},{"id":"2402.09916","title":"BUSTER: a \"BUSiness Transaction Entity Recognition\" dataset","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2407.01784","title":"Analyzing Persuasive Strategies in Meme Texts: A Fusion of Language Models with Paraphrase Enrichment","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2410.11119","title":"ChuLo: Chunk-Level Key Information Representation for Long Document Understanding","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2503.04305","title":"Computational Law: Datasets, Benchmarks, and Ontologies","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.16078","title":"Small Language Models in the Real World: Insights from Industrial Text Classification","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.05282","title":"Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2512.18301","title":"InstructNet: A Novel Approach for Multi-Label Instruction Classification through Advanced Deep Learning","created":"2025-12-20","cited_by_count":2,"area":null},{"id":"2203.06224","title":"verBERT: Automating Brazilian Case Law Document Multi-label Categorization Using BERT","created":"2022-03-11","cited_by_count":1,"area":null},{"id":"2301.04339","title":"Topics in Contextualised Attention Embeddings","created":"2023-01-11","cited_by_count":1,"area":null},{"id":"2305.02558","title":"Analyzing Hong Kong's Legal Judgments from a Computational Linguistics point-of-view","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2308.01413","title":"LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning","created":"2023-07-30","cited_by_count":1,"area":null},{"id":"2308.11531","title":"Empowering Refugee Claimants and their Lawyers: Using Machine Learning to Examine Decision-Making in Refugee Law","created":"2023-08-22","cited_by_count":1,"area":null},{"id":"2401.11852","title":"The Right Model for the Job: An Evaluation of Legal Multi-Label Classification Baselines","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2402.08209","title":"Thresholding Data Shapley for Data Cleansing Using Multi-Armed Bandits","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2412.13205","title":"Adaptive Two-Phase Finetuning LLMs for Japanese Legal Text Retrieval","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2507.02846","title":"Legal Requirements Translation from Law","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2508.02029","title":"A Confidence-Diversity Framework for Calibrating AI Judgement in Accessible Qualitative Coding Tasks","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.19997","title":"Exploring Selective Retrieval-Augmentation for Long-Tail Legal Text Classification","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2509.00990","title":"Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2603.12191","title":"Long-Context Encoder Models for Polish Language Understanding","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.15203","title":"MADE: A Living Benchmark for Multi-Label Text Classification with Uncertainty Quantification of Medical Device Adverse Events","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2606.27069","title":"Towards Explainable Adjudicative Variance: Quantifying Judicial Discretion via Gated Multi-Task Learning","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2106.03161","title":"Identifying Populist Paragraphs in Text: A machine-learning approach","created":"2021-06-06","cited_by_count":0,"area":null},{"id":"2111.14192","title":"Zero-Shot Cross-Lingual Transfer in Legal Domain Using Transformer Models","created":"2021-11-28","cited_by_count":0,"area":null},{"id":"2206.11187","title":"Automated Compliance Blueprint Optimization with Artificial Intelligence","created":"2022-06-22","cited_by_count":0,"area":null},{"id":"2303.01064","title":"Adopting the Multi-answer Questioning Task with an Auxiliary Metric for Extreme Multi-label Text Classification Utilizing the Label Hierarchy","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2305.05302","title":"The Perfect Victim: Computational Analysis of Judicial Attitudes towards Victims of Sexual Violence","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2305.18977","title":"Cross Encoding as Augmentation: Towards Effective Educational Text Classification","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2306.06190","title":"$FastDoc$: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2401.03946","title":"TextMachina: Seamless Generation of Machine-Generated Text Datasets","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2407.20673","title":"Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection","created":"2024-07-30","cited_by_count":0,"area":null},{"id":"2408.02233","title":"A Multi-Source Heterogeneous Knowledge Injected Prompt Learning Method for Legal Charge Prediction","created":"2024-08-05","cited_by_count":0,"area":null},{"id":"2408.03202","title":"A Debiased Nearest Neighbors Framework for Multi-Label Text Classification","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2508.03175","title":"Adaptive Sparse Softmax: An Effective and Efficient Softmax Variant","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2508.07592","title":"IBPS: Indian Bail Prediction System","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2512.24997","title":"Classifying long legal documents using short random chunks","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.24174","title":"Task-Centric Acceleration of Small-Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2604.22292","title":"ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text Classification","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.10339","title":"An Annotation Scheme and Classifier for Personal Facts in Dialogue","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.16767","title":"Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.31081","title":"Usage frequency and application variety of research methods in library and information science: Continuous investigation from 1991 to 2021","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.14882","title":"Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.20636","title":"MIL-BERT: Classification of Arbitrarily Large Text with Performance and Explanatory Guarantees","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.01379","title":"Polish ModernBERT: The Long and Short of Polish Language Understanding","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.39189","title":"ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World Consultations","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}