{"total":310,"rows":[{"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,"area":"lr"},{"id":"2306.16092","title":"Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture","created":"2023-06-28","cited_by_count":122,"area":"agents"},{"id":"2408.10343","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","created":"2024-08-19","cited_by_count":118,"area":"rag"},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"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":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81,"area":null},{"id":"2404.04302","title":"CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering","created":"2024-04-04","cited_by_count":72,"area":"lr"},{"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":"2212.14402","title":"GPT Takes the Bar Exam","created":"2022-12-29","cited_by_count":65,"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":"2305.07507","title":"LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development","created":"2023-05-12","cited_by_count":54,"area":null},{"id":"2310.09241","title":"Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration","created":"2023-10-13","cited_by_count":52,"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":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49,"area":null},{"id":"2204.06683","title":"Revisiting Transformer-based Models for Long Document Classification","created":"2022-04-14","cited_by_count":49,"area":null},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48,"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":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44,"area":null},{"id":"2402.09977","title":"Fast Vocabulary Transfer for Language Model Compression","created":"2024-02-15","cited_by_count":42,"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":"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":"2210.05529","title":"An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification","created":"2022-10-11","cited_by_count":38,"area":null},{"id":"2302.12039","title":"Natural Language Processing in the Legal Domain","created":"2023-02-23","cited_by_count":38,"area":null},{"id":"2409.20288","title":"LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models","created":"2024-09-30","cited_by_count":37,"area":null},{"id":"2203.08556","title":"LEVEN: A Large-Scale Chinese Legal Event Detection Dataset","created":"2022-03-16","cited_by_count":36,"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":"2312.06185","title":"KnowGPT: Knowledge Graph based Prompting for Large Language Models","created":"2023-12-11","cited_by_count":31,"area":null},{"id":"2212.00196","title":"Data-Efficient Finetuning Using Cross-Task Nearest Neighbors","created":"2022-12-01","cited_by_count":26,"area":null},{"id":"2210.13836","title":"Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts","created":"2022-10-25","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"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":"2502.20640","title":"LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation","created":"2025-02-28","cited_by_count":19,"area":"rag"},{"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":"2209.06120","title":"LegalBench: Prototyping a Collaborative Benchmark for Legal Reasoning","created":"2022-09-13","cited_by_count":17,"area":null},{"id":"2211.00582","title":"ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US","created":"2022-11-01","cited_by_count":17,"area":null},{"id":"2402.09949","title":"Multi-word Tokenization for Sequence Compression","created":"2024-02-15","cited_by_count":17,"area":null},{"id":"2208.08225","title":"On the Role of Negative Precedent in Legal Outcome Prediction","created":"2022-08-17","cited_by_count":16,"area":null},{"id":"2209.12325","title":"An Empirical Study on Cross-X Transfer for Legal Judgment Prediction","created":"2022-09-25","cited_by_count":16,"area":null},{"id":"2210.15497","title":"LSG Attention: Extrapolation of pretrained Transformers to long sequences","created":"2022-10-13","cited_by_count":16,"area":null},{"id":"2210.06277","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","created":"2022-10-12","cited_by_count":14,"area":null},{"id":"2302.00609","title":"Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases","created":"2023-02-01","cited_by_count":14,"area":null},{"id":"2310.11878","title":"From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification","created":"2023-10-18","cited_by_count":14,"area":null},{"id":"2211.17135","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","created":"2022-11-30","cited_by_count":13,"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":"2507.04037","title":"Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments","created":"2025-07-05","cited_by_count":13,"area":"agents"},{"id":"2210.13712","title":"Parameter-Efficient Legal Domain Adaptation","created":"2022-10-25","cited_by_count":12,"area":null},{"id":"2302.00768","title":"Leveraging Task Dependency and Contrastive Learning for Case Outcome Classification on European Court of Human Rights Cases","created":"2023-02-01","cited_by_count":12,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"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":"2510.06999","title":"Towards Reliable Retrieval in RAG Systems for Large Legal Datasets","created":"2025-10-08","cited_by_count":12,"area":"rag"},{"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":"2503.01372","title":"SwiLTra-Bench: The Swiss Legal Translation Benchmark","created":"2025-03-03","cited_by_count":11,"area":null},{"id":"2509.00761","title":"L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit","created":"2025-08-31","cited_by_count":11,"area":"agents"},{"id":"2609.27678","title":"Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding","created":"2026-09-23","cited_by_count":11,"area":null},{"id":"2301.04253","title":"Towards Answering Climate Questionnaires from Unstructured Climate Reports","created":"2023-01-11","cited_by_count":10,"area":null},{"id":"2311.09693","title":"BLT: Can Large Language Models Handle Basic Legal Text?","created":"2023-11-16","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":"2406.15313","title":"STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals","created":"2024-06-21","cited_by_count":10,"area":null},{"id":"2410.12974","title":"BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks","created":"2024-10-16","cited_by_count":10,"area":null},{"id":"2412.15291","title":"A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science","created":"2024-12-19","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":"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":"2601.06586","title":"Detecting LLM-Generated Text with Performance Guarantees","created":"2026-01-10","cited_by_count":10,"area":null},{"id":"2305.08428","title":"Legal Extractive Summarization of U.S. Court Opinions","created":"2023-05-15","cited_by_count":9,"area":null},{"id":"2306.05431","title":"LexGPT 0.1: pre-trained GPT-J models with Pile of Law","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2402.07214","title":"Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification","created":"2024-02-11","cited_by_count":9,"area":null},{"id":"2410.07035","title":"PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness","created":"2024-10-09","cited_by_count":9,"area":"lr"},{"id":"2502.05675","title":"Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning","created":"2025-02-08","cited_by_count":9,"area":"lr"},{"id":"2502.08825","title":"Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts","created":"2025-02-12","cited_by_count":9,"area":null},{"id":"2609.37647","title":"Evaluating and Benchmarking the System One Model Jev","created":"2026-09-29","cited_by_count":9,"area":null},{"id":"2211.02950","title":"The Legal Argument Reasoning Task in Civil Procedure","created":"2022-11-05","cited_by_count":8,"area":"lr"},{"id":"2301.10095","title":"Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards","created":"2023-01-24","cited_by_count":8,"area":null},{"id":"2310.14346","title":"The Law and NLP: Bridging Disciplinary Disconnects","created":"2023-10-22","cited_by_count":8,"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":"2502.20364","title":"Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization","created":"2025-02-27","cited_by_count":8,"area":"rag"},{"id":"2507.21134","title":"TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law","created":"2025-07-22","cited_by_count":8,"area":"safety"},{"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":"2605.20270","title":"Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs","created":"2026-05-18","cited_by_count":8,"area":null},{"id":"2305.16259","title":"Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2306.07111","title":"Linear Classifier: An Often-Forgotten Baseline for Text Classification","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2308.04138","title":"Large Language Model Prompt Chaining for Long Legal Document Classification","created":"2023-08-08","cited_by_count":7,"area":null},{"id":"2310.16607","title":"On the Interplay between Fairness and Explainability","created":"2023-10-25","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":"2406.01283","title":"Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification","created":"2024-06-03","cited_by_count":7,"area":"inference"},{"id":"2506.12213","title":"Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation","created":"2025-06-13","cited_by_count":7,"area":null},{"id":"2407.18990","title":"Stay Tuned: An Empirical Study of the Impact of Hyperparameters on LLM Tuning in Real-World Applications","created":"2024-07-25","cited_by_count":6,"area":null},{"id":"2409.13721","title":"LegiLM: A Fine-Tuned Legal Language Model for Data Compliance","created":"2024-09-09","cited_by_count":6,"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":"2411.05978","title":"The Empirical Impact of Data Sanitization on Language Models","created":"2024-11-08","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":"2510.20941","title":"Do LLMs Truly Understand When a Precedent Is Overruled?","created":"2025-10-23","cited_by_count":6,"area":null},{"id":"2511.00340","title":"Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2211.11724","title":"Legal and Political Stance Detection of SCOTUS Language","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2305.06545","title":"GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark","created":"2023-05-11","cited_by_count":5,"area":null}],"next_cursor":"100"}