{"list":"other","total":51,"rows":[{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"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},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"1906.02059","title":"Neural Legal Judgment Prediction in English","created":"2019-06-05","cited_by_count":209},{"id":"1807.02478","title":"CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction","created":"2018-07-04","cited_by_count":170},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148},{"id":"1910.00523","title":"BillSum: A Corpus for Automatic Summarization of US Legislation","created":"2019-10-01","cited_by_count":117},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"2301.13126","title":"LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain","created":"2023-01-30","cited_by_count":68},{"id":"1911.00841","title":"Question Answering for Privacy Policies: Combining Computational and Legal Perspectives","created":"2019-11-03","cited_by_count":67},{"id":"2005.05257","title":"A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering","created":"2020-05-11","cited_by_count":62},{"id":"2110.00806","title":"Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark","created":"2021-10-02","cited_by_count":60},{"id":"2305.07507","title":"LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development","created":"2023-05-12","cited_by_count":54},{"id":"2505.12864","title":"LEXam: Benchmarking Legal Reasoning on 340 Law Exams","created":"2025-05-19","cited_by_count":54},{"id":"2310.09241","title":"Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration","created":"2023-10-13","cited_by_count":52},{"id":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49},{"id":"2206.10883","title":"Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities","created":"2022-06-22","cited_by_count":47},{"id":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44},{"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},{"id":"2310.17609","title":"LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset","created":"2023-10-26","cited_by_count":38},{"id":"2408.08089","title":"AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents","created":"2024-08-15","cited_by_count":37},{"id":"2409.20288","title":"LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models","created":"2024-09-30","cited_by_count":37},{"id":"2203.08556","title":"LEVEN: A Large-Scale Chinese Legal Event Detection Dataset","created":"2022-03-16","cited_by_count":36},{"id":"2309.17050","title":"Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models","created":"2023-09-29","cited_by_count":35},{"id":"2301.00876","title":"MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding","created":"2023-01-02","cited_by_count":33},{"id":"2511.11562","title":"PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning","created":"2025-11-14","cited_by_count":32},{"id":"1906.00424","title":"Plain English Summarization of Contracts","created":"2019-06-02","cited_by_count":28},{"id":"1905.10892","title":"Extreme Multi-Label Legal Text Classification: A case study in EU Legislation","created":"2019-05-26","cited_by_count":26},{"id":"2211.03442","title":"Named Entity Recognition in Indian court judgments","created":"2022-11-07","cited_by_count":26},{"id":"2210.07544","title":"Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation","created":"2022-10-14","cited_by_count":24},{"id":"2103.02381","title":"Human-AI Interactions in Public Sector Decision-Making: \"Automation Bias\" and \"Selective Adherence\" to Algorithmic Advice","created":"2021-03-03","cited_by_count":22},{"id":"2207.04182","title":"Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Extraction","created":"2022-07-09","cited_by_count":21},{"id":"2306.01966","title":"GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation","created":"2023-06-03","cited_by_count":19},{"id":"2312.05762","title":"Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning","created":"2023-12-10","cited_by_count":19},{"id":"2407.05399","title":"IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning","created":"2024-07-07","cited_by_count":16},{"id":"2412.14556","title":"CitaLaw: Enhancing LLM with Citations in Legal Domain","created":"2024-12-19","cited_by_count":16},{"id":"2403.04454","title":"Low-Resource Court Judgment Summarization for Common Law Systems","created":"2024-03-07","cited_by_count":11},{"id":"2410.06581","title":"Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs","created":"2024-10-09","cited_by_count":11},{"id":"2205.08478","title":"An Evaluation Framework for Legal Document Summarization","created":"2022-05-17","cited_by_count":10},{"id":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10},{"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},{"id":"2310.05620","title":"LAiW: A Chinese Legal Large Language Models Benchmark","created":"2023-10-09","cited_by_count":9},{"id":"2310.15602","title":"MUSER: A Multi-View Similar Case Retrieval Dataset","created":"2023-10-24","cited_by_count":8},{"id":"2305.01211","title":"MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset","created":"2023-05-02","cited_by_count":7},{"id":"2503.18360","title":"J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain","created":"2025-03-24","cited_by_count":7},{"id":"2404.03150","title":"NLP at UC Santa Cruz at SemEval-2024 Task 5: Legal Answer Validation using Few-Shot Multi-Choice QA","created":"2024-04-04","cited_by_count":2},{"id":"2305.18315","title":"CDJUR-BR -- A Golden Collection of Legal Document from Brazilian Justice with Fine-Grained Named Entities","created":"2023-05-20","cited_by_count":1},{"id":"2507.10852","title":"LLMs on Trial: Evaluating Judicial Fairness for Large Language Models","created":"2025-07-14","cited_by_count":1}],"next_cursor":null}