{"total":50,"rows":[{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2404.04302","title":"CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering","created":"2024-04-04","cited_by_count":72,"area":"lr"},{"id":"2502.17638","title":"Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law","created":"2025-02-24","cited_by_count":30,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2411.01829","title":"Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically","created":"2024-11-04","cited_by_count":22,"area":"lr"},{"id":"2410.04526","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","created":"2024-10-06","cited_by_count":20,"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":"2407.05399","title":"IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning","created":"2024-07-07","cited_by_count":16,"area":"lr"},{"id":"2511.04662","title":"VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks","created":"2025-11-06","cited_by_count":11,"area":"lr"},{"id":"2510.07243","title":"LeMAJ (Legal LLM-as-a-Judge): Bridging Legal Reasoning and LLM Evaluation","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"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,"area":"lr"},{"id":"2502.05675","title":"Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning","created":"2025-02-08","cited_by_count":9,"area":"lr"},{"id":"2505.10571","title":"On the Failure of Latent State Persistence in Large Language Models","created":"2025-04-30","cited_by_count":9,"area":"lr"},{"id":"2505.22959","title":"LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements","created":"2025-05-29","cited_by_count":9,"area":"lr"},{"id":"2508.07827","title":"Evaluating Large Language Models as Expert Annotators","created":"2025-08-11","cited_by_count":9,"area":"lr"},{"id":"2603.07539","title":"MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs","created":"2026-03-08","cited_by_count":8,"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":"2608.12875","title":"The Embedder's Dilemma: LLMs Are Better, but at What Cost?","created":"2026-08-13","cited_by_count":5,"area":"lr"},{"id":"2406.04046","title":"ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints","created":"2024-06-06","cited_by_count":4,"area":"lr"},{"id":"2410.12621","title":"Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning","created":"2024-10-16","cited_by_count":4,"area":"lr"},{"id":"2410.13352","title":"LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights","created":"2024-10-17","cited_by_count":4,"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":"2601.08134","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":"2602.18916","title":"Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoning","created":"2026-02-21","cited_by_count":4,"area":"lr"},{"id":"2505.19259","title":"Towards Large Reasoning Models for Agriculture","created":"2025-05-25","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":"2602.06359","title":"Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2406.06863","title":"Ollabench: Evaluating LLMs' Reasoning for Human-centric Interdependent Cybersecurity","created":"2024-06-11","cited_by_count":2,"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":"2510.17900","title":"Are LLMs Court-Ready? Evaluating Frontier Models on Indian Legal Reasoning","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"id":"2604.27713","title":"Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning","created":"2026-04-30","cited_by_count":2,"area":"lr"},{"id":"2510.03349","title":"AgentCaster: Reasoning-Guided Tornado Forecasting","created":"2025-10-02","cited_by_count":1,"area":"lr"},{"id":"2511.06618","title":"GRAPH-GRPO-LEX: Contract Graph Modeling and Reinforcement Learning with Group Relative Policy Optimization","created":"2025-11-10","cited_by_count":1,"area":"lr"},{"id":"2604.16396","title":"QU-NLP at QIAS 2026: Multi-Stage QLoRA Fine-Tuning for Arabic Islamic Inheritance Reasoning","created":"2026-03-29","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":"2607.14506","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","created":"2026-07-16","cited_by_count":1,"area":"lr"},{"id":"2602.18095","title":"Neurosymbolic Language Reasoning as Satisfiability Modulo Theory","created":"2026-02-20","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":"2605.09270","title":"Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.16052","title":"Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law","created":"2026-05-15","cited_by_count":0,"area":"lr"},{"id":"2605.24573","title":"AstroMind: A High-Fidelity Benchmark for Spacecraft Behavior Reasoning Based on Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2607.03957","title":"NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO","created":"2026-07-04","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"},{"id":"2608.29616","title":"JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.05928","title":"Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems","created":"2026-09-05","cited_by_count":0,"area":"lr"},{"id":"2610.06439","title":"Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.13695","title":"Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}