{"total":39,"rows":[{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2301.13126","title":"LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain","created":"2023-01-30","cited_by_count":68,"area":null},{"id":"2305.07507","title":"LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development","created":"2023-05-12","cited_by_count":54,"area":null},{"id":"2309.12269","title":"The Cambridge Law Corpus: A Dataset for Legal AI Research","created":"2023-09-21","cited_by_count":14,"area":null},{"id":"2404.11826","title":"AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence","created":"2024-04-18","cited_by_count":12,"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":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2506.07443","title":"LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2403.04791","title":"LLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Dataset","created":"2024-03-04","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":"2409.07055","title":"Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction","created":"2024-09-11","cited_by_count":5,"area":null},{"id":"2409.08098","title":"The CLC-UKET Dataset: Benchmarking Case Outcome Prediction for the UK Employment Tribunal","created":"2024-09-12","cited_by_count":5,"area":null},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2410.08731","title":"Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2211.01692","title":"Data-efficient End-to-end Information Extraction for Statistical Legal Analysis","created":"2022-11-03","cited_by_count":3,"area":null},{"id":"2507.07748","title":"When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2403.06537","title":"On the Consideration of AI Openness: Can Good Intent Be Abused?","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2502.16357","title":"LegalBench.PT: A Benchmark for Portuguese Law","created":"2025-02-22","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":"2505.19667","title":"LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2409.18645","title":"The Craft of Selective Prediction: Towards Reliable Case Outcome Classification -- An Empirical Study on European Court of Human Rights Cases","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2502.06147","title":"LegalViz: Legal Text Visualization by Text To Diagram Generation","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2506.02561","title":"Pruning General Large Language Models into Customized Expert Models","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.15266","title":"Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgments","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2511.22869","title":"JBE-QA: Japanese Bar Exam QA Dataset for Assessing Legal Domain Knowledge","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2601.03553","title":"Evaluating LLMs for Police Decision-Making: A Framework Based on Police Action Scenarios","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.15267","title":"Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2604.06173","title":"Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA","created":"2026-01-24","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":"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":"2401.14654","title":"A Korean Legal Judgment Prediction Dataset for Insurance Disputes","created":"2024-01-26","cited_by_count":0,"area":null},{"id":"2403.16444","title":"KIT-19: A Comprehensive Korean Instruction Toolkit on 19 Tasks for Fine-Tuning Korean Large Language Models","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2406.10974","title":"Towards Supporting Legal Argumentation with NLP: Is More Data Really All You Need?","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2412.11787","title":"A Method for Detecting Legal Article Competition for Korean Criminal Law Using a Case-augmented Mention Graph","created":"2024-12-16","cited_by_count":0,"area":null},{"id":"2605.03792","title":"TriBench-Ko: Evaluating LLM Risks in Judicial Workflows","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2607.17111","title":"BLAD: A Historically Contextualized, Multilingual Dataset of Bangladeshi Legal Acts (1799 to 2025)","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2607.18825","title":"AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.09887","title":"When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2610.00087","title":"Legal text classification in Korean sexual offense cases: from traditional machine learning to large language models with XAI insights","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}