{"total":22,"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":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2506.12364","title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval","created":"2025-06-14","cited_by_count":21,"area":"lr"},{"id":"2402.10400","title":"Chain of Logic: Rule-Based Reasoning with Large Language Models","created":"2024-02-16","cited_by_count":18,"area":"lr"},{"id":"2310.14880","title":"Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?","created":"2023-10-23","cited_by_count":12,"area":"lr"},{"id":"2508.07827","title":"Evaluating Large Language Models as Expert Annotators","created":"2025-08-11","cited_by_count":9,"area":"lr"},{"id":"2510.08710","title":"Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning","created":"2025-10-09","cited_by_count":7,"area":"lr"},{"id":"2511.00340","title":"Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2601.04758","title":"PILOT-Bench: A Benchmark for Legal Reasoning in the Patent Domain with IRAC-Aligned Classification Tasks","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2601.13183","title":"OpenExempt: A Diagnostic Benchmark for Legal Reasoning and a Framework for Creating Custom Benchmarks on Demand","created":"2026-01-19","cited_by_count":3,"area":"lr"},{"id":"2506.04636","title":"CHANCERY: Evaluating Corporate Governance Reasoning Capabilities in Language Models","created":"2025-06-05","cited_by_count":2,"area":"lr"},{"id":"2510.00694","title":"ALARB: An Arabic Legal Argument Reasoning Benchmark","created":"2025-10-01","cited_by_count":2,"area":"lr"},{"id":"2507.18857","title":"PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2605.29170","title":"UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.29738","title":"Multi-Legal-Bench: Evaluating LLMs on Legal Reasoning Across Jurisdictions, Languages, and Legal Traditions","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2605.31238","title":"Scaling Multi-Hop Training Data via Graph-Constrained Path Selection","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.14506","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","created":"2026-07-16","cited_by_count":1,"area":"lr"},{"id":"2601.01825","title":"CSCBench: A PVC Diagnostic Benchmark for Commodity Supply Chain Reasoning","created":"2026-01-05","cited_by_count":0,"area":"lr"},{"id":"2605.02472","title":"Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication","created":"2026-05-04","cited_by_count":0,"area":"lr"},{"id":"2608.14610","title":"When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2608.26832","title":"RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}