{"list":"other","total":52,"rows":[{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"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":"2103.06268","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","created":"2021-03-10","cited_by_count":236},{"id":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128},{"id":"2408.10343","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","created":"2024-08-19","cited_by_count":118},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74},{"id":"2206.04737","title":"Outsider Oversight: Designing a Third Party Audit Ecosystem for AI Governance","created":"2022-06-09","cited_by_count":67},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60},{"id":"2412.17259","title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","created":"2024-12-23","cited_by_count":59},{"id":"2310.02521","title":"Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem","created":"2023-10-04","cited_by_count":52},{"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":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39},{"id":"2502.17041","title":"PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance","created":"2025-02-24","cited_by_count":37},{"id":"2505.03970","title":"A Reasoning-Focused Legal Retrieval Benchmark","created":"2025-05-06","cited_by_count":37},{"id":"2301.00876","title":"MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding","created":"2023-01-02","cited_by_count":33},{"id":"2409.11968","title":"Efficacy of Synthetic Data as a Benchmark","created":"2024-09-18","cited_by_count":30},{"id":"2405.10632","title":"Towards interactive evaluations for interaction harms in human-AI systems","created":"2024-05-17","cited_by_count":29},{"id":"1912.09156","title":"CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension","created":"2019-12-19","cited_by_count":26},{"id":"2010.10386","title":"A Benchmark for Lease Contract Review","created":"2020-10-20","cited_by_count":26},{"id":"2410.07959","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","created":"2024-10-10","cited_by_count":24},{"id":"2111.05071","title":"Conformity Assessments and Post-market Monitoring: A Guide to the Role of Auditing in the Proposed European AI Regulation","created":"2021-11-09","cited_by_count":19},{"id":"2208.12645","title":"The Brussels Effect and Artificial Intelligence: How EU regulation will impact the global AI market","created":"2022-08-23","cited_by_count":18},{"id":"2503.14258","title":"JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System","created":"2025-03-18","cited_by_count":18},{"id":"2502.04498","title":"Verifiable Format Control for Large Language Model Generations","created":"2025-02-06","cited_by_count":17},{"id":"2306.09237","title":"One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support","created":"2023-06-15","cited_by_count":16},{"id":"2306.03324","title":"How Effective are Large Language Models in Generating Software Specifications?","created":"2023-06-06","cited_by_count":12},{"id":"2407.12454","title":"ExploreGen: Large Language Models for Envisioning the Uses and Risks of AI Technologies","created":"2024-07-17","cited_by_count":12},{"id":"2501.06582","title":"ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting","created":"2025-01-11","cited_by_count":11},{"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},{"id":"2404.17522","title":"Enhancing Legal Compliance and Regulation Analysis with Large Language Models","created":"2024-04-26","cited_by_count":10},{"id":"2407.17374","title":"Co-designing an AI Impact Assessment Report Template with AI Practitioners and AI Compliance Experts","created":"2024-07-24","cited_by_count":10},{"id":"2505.22959","title":"LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements","created":"2025-05-29","cited_by_count":9},{"id":"2505.13673","title":"Comparing Apples to Oranges: A Taxonomy for Navigating the Global Landscape of AI Regulation","created":"2025-05-19","cited_by_count":7},{"id":"2403.09163","title":"Caveat Lector: Large Language Models in Legal Practice","created":"2024-03-14","cited_by_count":6},{"id":"2405.10248","title":"Co-Matching: Towards Human-Machine Collaborative Legal Case Matching","created":"2024-05-16","cited_by_count":6},{"id":"2407.07300","title":"From Principles to Rules: A Regulatory Approach for Frontier AI","created":"2024-07-10","cited_by_count":6},{"id":"2506.01931","title":"Red Teaming AI Policy: A Taxonomy of Avoision and the EU AI Act","created":"2025-06-02","cited_by_count":6},{"id":"2508.05464","title":"Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?","created":"2025-08-07","cited_by_count":6},{"id":"2406.04202","title":"Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model","created":"2024-06-06","cited_by_count":5},{"id":"2412.20602","title":"NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documents","created":"2024-12-29","cited_by_count":4},{"id":"2406.14758","title":"Compliance Cards: Automated EU AI Act Compliance Analyses amidst a Complex AI Supply Chain","created":"2024-06-20","cited_by_count":3},{"id":"2505.01307","title":"Document Retrieval Augmented Fine-Tuning (DRAFT) for safety-critical software assessments","created":"2025-05-02","cited_by_count":2},{"id":"2505.11946","title":"Let's have a chat with the EU AI Act","created":"2025-05-17","cited_by_count":2},{"id":"2508.09713","title":"Evaluating the Role of Large Language Models in Legal Practice in India","created":"2025-08-13","cited_by_count":2},{"id":"2504.00934","title":"InformGen: An AI Copilot for Accurate and Compliant Clinical Research Consent Document Generation","created":"2025-04-01","cited_by_count":1},{"id":"2505.14015","title":"AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation","created":"2025-05-20","cited_by_count":1},{"id":"2507.17514","title":"TAI Scan Tool: A RAG-Based Tool With Minimalistic Input for Trustworthy AI Self-Assessment","created":"2025-07-23","cited_by_count":1}],"next_cursor":null}