{"total":67,"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":"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,"area":null},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148,"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":"2401.02415","title":"LLaMA Pro: Progressive LLaMA with Block Expansion","created":"2024-01-04","cited_by_count":101,"area":null},{"id":"2306.02069","title":"MultiLegalPile: A 689GB Multilingual Legal Corpus","created":"2023-06-03","cited_by_count":60,"area":null},{"id":"2308.05342","title":"Metacognitive Prompting Improves Understanding in Large Language Models","created":"2023-08-10","cited_by_count":58,"area":null},{"id":"2204.04859","title":"A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges","created":"2022-04-11","cited_by_count":50,"area":null},{"id":"2309.09530","title":"Adapting Large Language Models to Domains via Reading Comprehension","created":"2023-09-18","cited_by_count":50,"area":null},{"id":"2206.10883","title":"Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities","created":"2022-06-22","cited_by_count":47,"area":null},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47,"area":null},{"id":"2109.14076","title":"RAFT: A Real-World Few-Shot Text Classification Benchmark","created":"2021-09-28","cited_by_count":44,"area":null},{"id":"2410.21306","title":"Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges","created":"2024-10-25","cited_by_count":42,"area":null},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40,"area":null},{"id":"2301.00876","title":"MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding","created":"2023-01-02","cited_by_count":33,"area":null},{"id":"2304.12202","title":"ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark","created":"2023-03-09","cited_by_count":33,"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":"2501.05559","title":"Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2308.05502","title":"Bringing order into the realm of Transformer-based language models for artificial intelligence and law","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2311.09825","title":"Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks","created":"2023-11-16","cited_by_count":13,"area":null},{"id":"2405.14211","title":"ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks","created":"2024-05-23","cited_by_count":11,"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":"2305.12576","title":"Automated Few-shot Classification with Instruction-Finetuned Language Models","created":"2023-05-21","cited_by_count":9,"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":"2106.05688","title":"AI-enabled Automation for Completeness Checking of Privacy Policies","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2403.02799","title":"DPPA: Pruning Method for Large Language Model to Model Merging","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2407.16615","title":"Lawma: The Power of Specialization for Legal Annotation","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2410.02330","title":"Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection","created":"2024-10-03","cited_by_count":6,"area":null},{"id":"2507.21108","title":"A Survey of Classification Tasks and Approaches for Legal Contracts","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2109.07234","title":"The Unreasonable Effectiveness of the Baseline: Discussing SVMs in Legal Text Classification","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2410.12857","title":"Enterprise Benchmarks for Large Language Model Evaluation","created":"2024-10-11","cited_by_count":5,"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":"2507.19995","title":"VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering","created":"2025-07-26","cited_by_count":4,"area":null},{"id":"2106.14438","title":"Traditional Machine Learning and Deep Learning Models for Argumentation Mining in Russian Texts","created":"2021-06-28","cited_by_count":3,"area":null},{"id":"2401.16429","title":"Combining topic modelling and citation network analysis to study case law from the European Court on Human Rights on the right to respect for private and family life","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2211.15556","title":"Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2312.01398","title":"Towards Mitigating Perceived Unfairness in Contracts from a Non-Legal Stakeholder's Perspective","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2402.16977","title":"Dealing with Data for RE: Mitigating Challenges while using NLP and Generative AI","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2405.06703","title":"Interpretable Cross-Examination Technique (ICE-T): Using highly informative features to boost LLM performance","created":"2024-05-08","cited_by_count":2,"area":null},{"id":"2508.07596","title":"From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2508.07849","title":"Evaluating Customized vs. Generalist Transformer-based Models for Legal Contract Classification","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2510.08524","title":"Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2110.00125","title":"Combining Transformers with Natural Language Explanations","created":"2021-09-02","cited_by_count":1,"area":null},{"id":"2306.17042","title":"Towards Grammatical Tagging for the Legal Language of Cybersecurity","created":"2023-06-29","cited_by_count":1,"area":null},{"id":"2311.01256","title":"An energy-based comparative analysis of common approaches to text classification in the Legal domain","created":"2023-11-02","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":"2402.14457","title":"Annotation and Classification of Relevant Clauses in Terms-and-Conditions Contracts","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2409.00077","title":"Are LLM-based methods good enough for detecting unfair terms of service?","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2502.00865","title":"Predicting potentially abusive clauses in Chilean terms of services with natural language processing","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2505.00479","title":"Computational Identification of Regulatory Statements in EU Legislation","created":"2025-05-01","cited_by_count":1,"area":null},{"id":"2507.01234","title":"The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure","created":"2025-07-01","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":"2110.15062","title":"SenTag: a Web-based Tool for Semantic Annotation of Textual Documents","created":"2021-09-16","cited_by_count":0,"area":null},{"id":"2111.00086","title":"Measuring a Texts Fairness Dimensions Using Machine Learning Based on Social Psychological Factors","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2301.10716","title":"Investigating Strategies for Clause Recommendation","created":"2023-01-21","cited_by_count":0,"area":null},{"id":"2305.03508","title":"CiteCaseLAW: Citation Worthiness Detection in Caselaw for Legal Assistive Writing","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2309.04146","title":"NESTLE: a No-Code Tool for Statistical Analysis of Legal Corpus","created":"2023-09-08","cited_by_count":0,"area":null},{"id":"2404.13087","title":"Demystifying Legalese: An Automated Approach for Summarizing and Analyzing Overlaps in Privacy Policies and Terms of Service","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2507.01734","title":"LLMs for Legal Subsumption in German Employment Contracts","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2508.00659","title":"Demo: TOSense -- What Did You Just Agree to?","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2510.22531","title":"Text to Trust: Evaluating Fine-Tuning and LoRA Trade-offs in Language Models for Unfair Terms of Service Detection","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2604.02276","title":"De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2607.13260","title":"Discourse-Aware Policy Analysis with Argumentation: A Hybrid LLM-Symbolic Framework for Disaster Governance","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.18424","title":"Enabling Multilingual Privacy Policy Audits: Large-Scale Analysis of Spanish Mobile Apps","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.02055","title":"Privacy Washing: Detecting Internal Contradictions in Privacy Policies","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.34986","title":"N\\\"urnberg NLP at ChildSafeAds 2026: Structurally Dissimilar Voter Ensembles under Four Levels of Data Access","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01345","title":"ARCCS: An Automated Regulatory Compliance Checking System","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}