{"total":90,"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":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"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":"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":"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":"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":"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":"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":"2210.13448","title":"EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain","created":"2022-10-24","cited_by_count":40,"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":"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":"2309.11285","title":"Overview of AuTexTification at IberLEF 2023: Detection and Attribution of Machine-Generated Text in Multiple Domains","created":"2023-09-20","cited_by_count":31,"area":null},{"id":"2311.05741","title":"Efficiently Adapting Pretrained Language Models To New Languages","created":"2023-11-09","cited_by_count":28,"area":null},{"id":"2201.13125","title":"Corpus for Automatic Structuring of Legal Documents","created":"2022-01-31","cited_by_count":25,"area":null},{"id":"2203.07856","title":"Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting","created":"2022-03-15","cited_by_count":23,"area":null},{"id":"2305.05627","title":"An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text","created":"2023-05-09","cited_by_count":23,"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":"2407.20743","title":"Meltemi: The first open Large Language Model for Greek","created":"2024-07-30","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":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","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":"2311.08890","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":"2204.00806","title":"HLDC: Hindi Legal Documents Corpus","created":"2022-04-02","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":"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":"2601.06586","title":"Detecting LLM-Generated Text with Performance Guarantees","created":"2026-01-10","cited_by_count":10,"area":null},{"id":"2308.07282","title":"Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification","created":"2023-08-14","cited_by_count":9,"area":null},{"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":"2306.04996","title":"T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification","created":"2023-06-08","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":"2305.01211","title":"MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset","created":"2023-05-02","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":"2509.11414","title":"Continually Adding New Languages to Multilingual Language Models","created":"2025-09-14","cited_by_count":7,"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":"2303.09421","title":"SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2311.01870","title":"Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval","created":"2023-11-03","cited_by_count":5,"area":null},{"id":"2403.00252","title":"EUROPA: A Legal Multilingual Keyphrase Generation Dataset","created":"2024-03-01","cited_by_count":5,"area":null},{"id":"2408.08981","title":"From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning","created":"2024-08-16","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2305.13058","title":"Retrieval-augmented Multi-label Text Classification","created":"2023-05-22","cited_by_count":3,"area":"rag"},{"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":"2309.10891","title":"Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2310.16356","title":"A Multi-Modal Multilingual Benchmark for Document Image Classification","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2403.12407","title":"Cross-Lingual Transfer for Natural Language Inference via Multilingual Prompt Translator","created":"2024-03-19","cited_by_count":3,"area":null},{"id":"2509.06195","title":"Language Bias in Information Retrieval: The Nature of the Beast and Mitigation Methods","created":"2025-09-07","cited_by_count":3,"area":null},{"id":"2510.13996","title":"The German Commons - 154 Billion Tokens of Openly Licensed Text for German Language Models","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2210.13086","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","created":"2022-10-24","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":"2506.04385","title":"MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2310.17233","title":"EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning","created":"2023-10-26","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":"2401.14135","title":"Convolutional Neural Networks can achieve binary bail judgement classification","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2406.04855","title":"The Russian Legislative Corpus","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2406.08796","title":"Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning","created":"2024-06-13","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":"2510.07877","title":"Ready to Translate, Not to Represent? Bias and Performance Gaps in Multilingual LLMs Across Language Families and Domains","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2510.20002","title":"Forging GEMs: Advancing Greek NLP through Quality-Based Corpus Curation","created":"2025-10-22","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":"2601.21525","title":"LMK > CLS: Landmark Pooling for Dense Embeddings","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.09570","title":"LEMUR: A Corpus for Robust Fine-Tuning of Multilingual Law Embedding Models for Retrieval","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.00920","title":"GPT-NL Public Corpus: A Permissively Licensed, Dutch-First Dataset for LLM Pre-training","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.22098","title":"Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.25701","title":"Neural Router: Semantic Content Matching for Agentic AI","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2606.04382","title":"LCSHBench: A Multilingual, Consensus-Grounded Benchmark for Library of Congress Subject Heading Assignment","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2608.26175","title":"Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors","created":"2026-07-27","cited_by_count":1,"area":"inference"},{"id":"2305.16521","title":"Label Agnostic Pre-training for Zero-shot Text Classification","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2401.14524","title":"Evaluating GPT-3.5's Awareness and Summarization Abilities for European Constitutional Texts with Shared Topics","created":"2024-01-25","cited_by_count":0,"area":null},{"id":"2408.11926","title":"Defining Boundaries: The Impact of Domain Specification on Cross-Language and Cross-Domain Transfer in Machine Translation","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2410.12852","title":"The Large Language Model GreekLegalRoBERTa","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2411.17941","title":"Multi-Label Bayesian Active Learning with Inter-Label Relationships","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2412.13809","title":"Extreme Multi-label Completion for Semantic Document Labelling with Taxonomy-Aware Parallel Learning","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2501.16011","title":"MEL: Legal Spanish Language Model","created":"2025-01-27","cited_by_count":0,"area":null},{"id":"2509.17367","title":"Scale-free Characteristics of Multilingual Legal Texts and the Limitations of LLMs","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2511.17402","title":"PUCP-Metrix: An Open-source and Comprehensive Toolkit for Linguistic Analysis of Spanish Texts","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2602.21379","title":"MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.16767","title":"Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.25263","title":"Mimir: Large-scale Multilingual Concept Modeling","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.30589","title":"ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.03898","title":"ANNOTARES: A Dataset for Extracting Logical Structures from German Statutory Texts","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.30757","title":"Which Rules Matter Now? Policy-Centroid Routing Before an Intelligent System Acts","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01322","title":"Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment","created":"2026-09-01","cited_by_count":0,"area":"mechinterp"},{"id":"2609.03597","title":"KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.02839","title":"To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}