{"total":84,"rows":[{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716,"area":null},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670,"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":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201,"area":null},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128,"area":null},{"id":"2309.11325","title":"DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services","created":"2023-09-20","cited_by_count":120,"area":null},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"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":"2212.14402","title":"GPT Takes the Bar Exam","created":"2022-12-29","cited_by_count":65,"area":null},{"id":"2402.18865","title":"Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning","created":"2024-02-29","cited_by_count":60,"area":null},{"id":"2305.15062","title":"Lawyer LLaMA Technical Report","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53,"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":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"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":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40,"area":null},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2406.11149","title":"GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory","created":"2024-06-17","cited_by_count":37,"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":"2406.04614","title":"LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model","created":"2024-06-07","cited_by_count":34,"area":null},{"id":"2402.17019","title":"Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling","created":"2024-02-26","cited_by_count":23,"area":null},{"id":"2105.07903","title":"Factoring Statutory Reasoning as Language Understanding Challenges","created":"2021-05-17","cited_by_count":20,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2412.14556","title":"CitaLaw: Enhancing LLM with Citations in Legal Domain","created":"2024-12-19","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":"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":"2505.20243","title":"It's High Time: A Survey of Temporal Question Answering","created":"2025-05-26","cited_by_count":14,"area":null},{"id":"2310.03328","title":"Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2103.13868","title":"Equality before the Law: Legal Judgment Consistency Analysis for Fairness","created":"2021-03-25","cited_by_count":11,"area":null},{"id":"2204.00806","title":"HLDC: Hindi Legal Documents Corpus","created":"2022-04-02","cited_by_count":11,"area":null},{"id":"2402.11176","title":"KnowTuning: Knowledge-aware Fine-tuning for Large Language Models","created":"2024-02-17","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":"2110.07333","title":"A Survey on Legal Question Answering Systems","created":"2021-10-12","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":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10,"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":"2501.04974","title":"SensorQA: A Question Answering Benchmark for Daily-Life Monitoring","created":"2025-01-09","cited_by_count":8,"area":null},{"id":"2506.01646","title":"ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2109.03731","title":"Cross-Policy Compliance Detection via Question Answering","created":"2021-09-08","cited_by_count":7,"area":null},{"id":"2403.18426","title":"TriviaHG: A Dataset for Automatic Hint Generation from Factoid Questions","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2102.01226","title":"Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data","created":"2021-02-01","cited_by_count":6,"area":null},{"id":"2410.05639","title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2112.13238","title":"PerCQA: Persian Community Question Answering Dataset","created":"2021-12-25","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":"2309.08173","title":"FedJudge: Federated Legal Large Language Model","created":"2023-09-15","cited_by_count":5,"area":null},{"id":"2403.04366","title":"Enhancing Court View Generation with Knowledge Injection and Guidance","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2407.19041","title":"Optimizing Numerical Estimation and Operational Efficiency in the Legal Domain through Large Language Models","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2412.07462","title":"Bilingual BSARD: Extending Statutory Article Retrieval to Dutch","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2504.04141","title":"Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2512.04578","title":"LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2107.06056","title":"Indian Legal NLP Benchmarks : A Survey","created":"2021-07-13","cited_by_count":3,"area":null},{"id":"2508.15213","title":"Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2202.13457","title":"Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks","created":"2022-02-27","cited_by_count":2,"area":null},{"id":"2407.16073","title":"KaPQA: Knowledge-Augmented Product Question-Answering","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2409.02840","title":"R2GQA: Retriever-Reader-Generator Question Answering System to Support Students Understanding Legal Regulations in Higher Education","created":"2024-09-04","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":"2511.09854","title":"TermGPT: Multi-Level Contrastive Fine-Tuning for Terminology Adaptation in Legal and Financial Domain","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2601.03725","title":"EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2606.09389","title":"LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2306.17042","title":"Towards Grammatical Tagging for the Legal Language of Cybersecurity","created":"2023-06-29","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":"2410.13013","title":"LEGAL-UQA: A Low-Resource Urdu-English Dataset for Legal Question Answering","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2506.03489","title":"EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2506.06060","title":"Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2508.17234","title":"ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation","created":"2025-08-24","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":"2601.15267","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":"2602.12639","title":"CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation","created":"2026-02-13","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":"2312.00584","title":"The Ethics of Automating Legal Actors","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2509.19485","title":"Identifying and Addressing User-level Security Concerns in Smart Homes Using \"Smaller\" LLMs","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2604.20549","title":"Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection","created":"2026-04-22","cited_by_count":0,"area":null},{"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":"2608.10268","title":"Toward Human Rights Benchmarking for LLMs: A Pilot Methodology","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.16010","title":"Nepali Legal Expertise through Generative and Extractive Pre-trained Transformers (NepLEGiT)","created":"2026-08-08","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},{"id":"2609.39189","title":"ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World Consultations","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.19992","title":"SoK: Grading Open-Text Legal Answers, from Law School Exams to Trustworthy Rubric Judges","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}