{"total":170,"rows":[{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853,"area":null},{"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":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176,"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":"2311.09774","title":"HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs","created":"2023-11-16","cited_by_count":92,"area":null},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2403.17752","title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?","created":"2024-03-26","cited_by_count":69,"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":"2402.01864","title":"(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice","created":"2024-02-02","cited_by_count":63,"area":null},{"id":"2306.02069","title":"MultiLegalPile: A 689GB Multilingual Legal Corpus","created":"2023-06-03","cited_by_count":60,"area":null},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57,"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":"2305.15062","title":"Lawyer LLaMA Technical Report","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2303.09136","title":"A Short Survey of Viewing Large Language Models in Legal Aspect","created":"2023-03-16","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":"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":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"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":"2305.11541","title":"Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering","created":"2023-05-19","cited_by_count":41,"area":null},{"id":"2302.12039","title":"Natural Language Processing in the Legal Domain","created":"2023-02-23","cited_by_count":38,"area":null},{"id":"2208.06178","title":"Mining Legal Arguments in Court Decisions","created":"2022-08-12","cited_by_count":35,"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":"2402.11597","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","created":"2024-02-18","cited_by_count":30,"area":null},{"id":"2501.06521","title":"Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering","created":"2025-01-11","cited_by_count":28,"area":null},{"id":"2211.03442","title":"Named Entity Recognition in Indian court judgments","created":"2022-11-07","cited_by_count":26,"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":"2209.01650","title":"ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining","created":"2022-09-04","cited_by_count":25,"area":null},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"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":"2403.08192","title":"MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension","created":"2024-03-13","cited_by_count":22,"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":"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":"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":"2407.02348","title":"Agreement-Based Cascading for Efficient Inference","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2505.24778","title":"Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?","created":"2025-05-30","cited_by_count":16,"area":null},{"id":"2305.12199","title":"VNHSGE: VietNamese High School Graduation Examination Dataset for Large Language Models","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2311.14966","title":"Walking a Tightrope -- Evaluating Large Language Models in High-Risk Domains","created":"2023-11-25","cited_by_count":15,"area":null},{"id":"2403.18365","title":"BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models","created":"2024-03-27","cited_by_count":15,"area":null},{"id":"2601.16669","title":"PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice","created":"2026-01-23","cited_by_count":15,"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":"2309.12269","title":"The Cambridge Law Corpus: A Dataset for Legal AI Research","created":"2023-09-21","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":"2501.05559","title":"Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives","created":"2025-01-09","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":"2405.06275","title":"Pruning as a Domain-specific LLM Extractor","created":"2024-05-10","cited_by_count":13,"area":null},{"id":"2106.10776","title":"Context-Aware Legal Citation Recommendation using Deep Learning","created":"2021-06-20","cited_by_count":12,"area":null},{"id":"2210.13712","title":"Parameter-Efficient Legal Domain Adaptation","created":"2022-10-25","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":"2301.05948","title":"tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation","created":"2023-01-14","cited_by_count":11,"area":null},{"id":"2404.08679","title":"Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector","created":"2024-04-07","cited_by_count":11,"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":"2211.02956","title":"Privacy-Preserving Models for Legal Natural Language Processing","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2403.02756","title":"Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models","created":"2024-03-05","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":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2210.12437","title":"Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance","created":"2022-10-22","cited_by_count":9,"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":"2306.00672","title":"Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking","created":"2023-06-01","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":"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":"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":"2510.03662","title":"Operationalizing Data Minimization for Privacy-Preserving LLM Prompting","created":"2025-10-04","cited_by_count":8,"area":null},{"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":"2210.09472","title":"Multi-granularity Argument Mining in Legal Texts","created":"2022-10-17","cited_by_count":7,"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":"2308.04138","title":"Large Language Model Prompt Chaining for Long Legal Document Classification","created":"2023-08-08","cited_by_count":7,"area":null},{"id":"2308.06942","title":"Approximating Human-Like Few-shot Learning with GPT-based Compression","created":"2023-08-14","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":"2109.06862","title":"Legal Transformer Models May Not Always Help","created":"2021-09-14","cited_by_count":6,"area":null},{"id":"2212.03222","title":"LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval","created":"2022-12-06","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":"2211.11724","title":"Legal and Political Stance Detection of SCOTUS Language","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2307.01458","title":"CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care","created":"2023-07-04","cited_by_count":5,"area":null},{"id":"2406.13217","title":"Automating IRAC Analysis in Malaysian Contract Law using a Semi-Structured Knowledge Base","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2409.07713","title":"Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justice","created":"2024-09-12","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":"2605.25240","title":"JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment","created":"2026-05-24","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":"2307.05081","title":"Argumentative Segmentation Enhancement for Legal Summarization","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2403.06872","title":"Exploring Large Language Models and Hierarchical Frameworks for Classification of Large Unstructured Legal Documents","created":"2024-03-11","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":"2409.18644","title":"Incorporating Precedents for Legal Judgement Prediction on European Court of Human Rights Cases","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2412.09807","title":"LLM Distillation for Efficient Few-Shot Multiple Choice Question Answering","created":"2024-12-13","cited_by_count":4,"area":null},{"id":"2412.14426","title":"All-in-One Tuning and Structural Pruning for Domain-Specific LLMs","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2502.18424","title":"Compressing Language Models for Specialized Domains","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2508.08011","title":"Optimal Transport Depth Up-Scaling","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2212.13428","title":"A Survey on Knowledge-Enhanced Pre-trained Language Models","created":"2022-12-27","cited_by_count":3,"area":null},{"id":"2307.11031","title":"Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2309.17280","title":"STRONG -- Structure Controllable Legal Opinion Summary Generation","created":"2023-09-29","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":"2410.10901","title":"3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection","created":"2024-10-13","cited_by_count":3,"area":null},{"id":"2504.16871","title":"Exploring How LLMs Capture and Represent Domain-Specific Knowledge","created":"2025-04-23","cited_by_count":3,"area":null}],"next_cursor":"100"}