{"total":54,"rows":[{"id":"2509.23808","title":"Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning","created":"2025-09-28","cited_by_count":17,"area":"lr"},{"id":"2505.17267","title":"GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations","created":"2025-05-22","cited_by_count":15,"area":"lr"},{"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":"2509.00761","title":"L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit","created":"2025-08-31","cited_by_count":11,"area":"agents"},{"id":"2506.19467","title":"Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?","created":"2025-06-24","cited_by_count":10,"area":"lr"},{"id":"2601.13433","title":"Who Endorsed It? Measuring Authority Bias Across Expertise Levels in Language Models","created":"2026-01-19","cited_by_count":8,"area":"lr"},{"id":"2505.18102","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2608.29856","title":"GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation","created":"2026-08-30","cited_by_count":5,"area":"synth"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2601.08134","title":"How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains","created":"2026-01-13","cited_by_count":4,"area":"lr"},{"id":"2507.07748","title":"When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2509.00529","title":"Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM Summarization","created":"2025-08-30","cited_by_count":3,"area":"lr"},{"id":"2509.22472","title":"Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2512.24572","title":"Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs' Legal Reasoning Capabilities","created":"2025-12-31","cited_by_count":3,"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":"2509.21856","title":"KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2602.09514","title":"EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies","created":"2026-02-10","cited_by_count":2,"area":"agents"},{"id":"2605.08437","title":"Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2606.03131","title":"HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2608.01292","title":"CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models","created":"2026-08-02","cited_by_count":2,"area":"lr"},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"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":"2603.23646","title":"Swiss-Bench SBP-002: A Frontier Model Comparison on Swiss Legal and Regulatory Tasks","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.20726","title":"Exploiting LLM-as-a-Judge Disposition on Free Text Legal QA via Prompt Optimization","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.16280","title":"Beyond Imperfect Alternatives with Rulemapping: A Neuro-Symbolic Case Study on Online Hate Speech","created":"2026-04-10","cited_by_count":1,"area":null},{"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":"2606.08932","title":"From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.25442","title":"PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models","created":"2026-06-24","cited_by_count":1,"area":"alignment"},{"id":"2608.15428","title":"Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks","created":"2026-08-15","cited_by_count":1,"area":null},{"id":"2608.18931","title":"Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck","created":"2026-08-19","cited_by_count":1,"area":"lr"},{"id":"2608.20204","title":"ContractScrub: A benchmark for final review of legal contracts","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2608.20220","title":"InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2609.14739","title":"Building Legal Reward Models for Grounding and Abstention","created":"2026-09-13","cited_by_count":1,"area":"rag"},{"id":"2510.25623","title":"Evaluating the Role of Verifiers in Test-Time Scaling for Legal Reasoning Tasks","created":"2025-10-29","cited_by_count":0,"area":"lr"},{"id":"2602.04687","title":"Investigating Disability Representations in Text-to-Image Models","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.26332","title":"CALRK-Bench: Evaluating Context-Aware Legal Reasoning in Korean Law","created":"2026-03-27","cited_by_count":0,"area":"lr"},{"id":"2604.09069","title":"NyayaMind- A Framework for Transparent Legal Reasoning and Judgment Prediction in the Indian Legal System","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.23730","title":"Expert Evaluation of LLM's Open-Ended Legal Reasoning on the Japanese Bar Exam Writing Task","created":"2026-04-26","cited_by_count":0,"area":"lr"},{"id":"2604.23809","title":"LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models","created":"2026-04-26","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":"2605.03792","title":"TriBench-Ko: Evaluating LLM Risks in Judicial Workflows","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.21076","title":"GradeLegal: Automated Grading for German Legal Cases","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.24454","title":"Decompose-and-Refine: Structured Legal Question Answering with Parametric Retrieval","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2605.28183","title":"BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.06941","title":"Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.23375","title":"Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts","created":"2026-06-22","cited_by_count":0,"area":"safety"},{"id":"2606.30906","title":"Investigating Multi-Agent Deliberation in Law","created":"2026-06-29","cited_by_count":0,"area":"agents"},{"id":"2607.09099","title":"L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2608.09393","title":"Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law","created":"2026-08-10","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":"2609.35561","title":"RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00353","title":"JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion","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}