{"total":68,"rows":[{"id":"2306.02069","title":"MultiLegalPile: A 689GB Multilingual Legal Corpus","created":"2023-06-03","cited_by_count":60,"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":"2306.05783","title":"Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation","created":"2023-06-09","cited_by_count":52,"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":"2403.02959","title":"AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation","created":"2024-03-05","cited_by_count":40,"area":"agents"},{"id":"2402.12204","title":"Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages","created":"2024-02-19","cited_by_count":36,"area":"distill"},{"id":"2409.13989","title":"ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models","created":"2024-09-21","cited_by_count":18,"area":null},{"id":"2407.05399","title":"IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning","created":"2024-07-07","cited_by_count":16,"area":"lr"},{"id":"2311.08890","title":"Large Language Models are legal but they are not: Making the case for a powerful LegalLLM","created":"2023-11-15","cited_by_count":12,"area":null},{"id":"2403.03866","title":"KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions","created":"2024-03-06","cited_by_count":11,"area":null},{"id":"2503.01372","title":"SwiLTra-Bench: The Swiss Legal Translation Benchmark","created":"2025-03-03","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":"2511.07979","title":"Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models","created":"2025-11-11","cited_by_count":10,"area":"lr"},{"id":"2404.00415","title":"CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP","created":"2024-03-30","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":"2405.05938","title":"DOLOMITES: Domain-Specific Long-Form Methodical Tasks","created":"2024-05-09","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":"2506.13044","title":"Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models","created":"2025-06-16","cited_by_count":8,"area":null},{"id":"2603.07539","title":"MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs","created":"2026-03-08","cited_by_count":8,"area":"lr"},{"id":"2305.01211","title":"MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset","created":"2023-05-02","cited_by_count":7,"area":null},{"id":"2402.17013","title":"Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset","created":"2024-02-26","cited_by_count":7,"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":"2403.00252","title":"EUROPA: A Legal Multilingual Keyphrase Generation Dataset","created":"2024-03-01","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":"2605.14890","title":"Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.24718","title":"The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty","created":"2026-05-23","cited_by_count":4,"area":null},{"id":"2309.08695","title":"Resolving Legalese: A Multilingual Exploration of Negation Scope Resolution in Legal Documents","created":"2023-09-15","cited_by_count":3,"area":null},{"id":"2310.04632","title":"Automatic Anonymization of Swiss Federal Supreme Court Rulings","created":"2023-10-07","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":"2402.07234","title":"CPSDBench: A Large Language Model Evaluation Benchmark and Baseline for Chinese Public Security Domain","created":"2024-02-11","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":"2503.08379","title":"JurisTCU: A Brazilian Portuguese Information Retrieval Dataset with Query Relevance Judgments","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2601.14160","title":"Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law","created":"2026-01-20","cited_by_count":2,"area":"synth"},{"id":"2605.17639","title":"Temporal Decay of Co-Citation Predictability: A 20-Year Statute Retrieval Benchmark from 396M Ukrainian Court Citations","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2605.21071","title":"Fine-grained Claim-level RAG Benchmark for Law","created":"2026-05-20","cited_by_count":2,"area":"rag"},{"id":"2306.07797","title":"Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2407.16516","title":"Assessing In-context Learning and Fine-tuning for Topic Classification of German Web Data","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2410.13460","title":"From Citations to Criticality: Predicting Legal Decision Influence in the Multilingual Swiss Jurisprudence","created":"2024-10-17","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":"2502.06147","title":"LegalViz: Legal Text Visualization by Text To Diagram Generation","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2503.04064","title":"Uncovering inequalities in new knowledge learning by large language models across different languages","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2508.10161","title":"LaajMeter: A Framework for LaaJ Evaluation","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2509.21208","title":"CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning Analysis","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"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":"2601.01331","title":"AppellateGen: A Benchmark for Appellate Legal Judgment Generation","created":"2026-01-04","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":"2603.23646","title":"Swiss-Bench SBP-002: A Frontier Model Comparison on Swiss Legal and Regulatory Tasks","created":"2026-03-24","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":"2605.25652","title":"A Two-Phase Stability Study of LLM Judges and Bar Council Examiners on Thai Bar-Exam Free-Form Essays","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.29170","title":"UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.29738","title":"Multi-Legal-Bench: Evaluating LLMs on Legal Reasoning Across Jurisdictions, Languages, and Legal Traditions","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2606.00898","title":"Citation Grounding Measures the Oracle: Graph Coverage Determines Reported LLM Hallucination Rates in Law","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2608.15428","title":"Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks","created":"2026-08-15","cited_by_count":1,"area":null},{"id":"2608.20220","title":"InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2410.12852","title":"The Large Language Model GreekLegalRoBERTa","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2508.03718","title":"Health Insurance Coverage Rule Interpretation Corpus: Law, Policy, and Medical Guidance for Health Insurance Coverage Understanding","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2604.12054","title":"REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.01486","title":"MAP-Law: Coverage-Driven Retrieval Control for Multi-Turn Legal Consultation","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.24452","title":"Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.23375","title":"Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts","created":"2026-06-22","cited_by_count":0,"area":"safety"},{"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":"2608.09393","title":"Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.10268","title":"Toward Human Rights Benchmarking for LLMs: A Pilot Methodology","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14210","title":"How Much Do Legal RAG Systems Still Hallucinate?","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.21409","title":"Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards?","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.30929","title":"Annotated Surrogate Retrieval for Polish Statutory Law","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.18908","title":"How Much is a Human Right Worth? ECtHR-NPD: A Benchmark for Predicting Non-Pecuniary Damage Awards","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}