JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/beita6969/JusticeAxis
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction
- VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction
- EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage
- Multi-Legal-Bench: When the Answer Is in the Input. Label Leakage in Legal Benchmarks Built from Court Registries
- Parthenon Law: A Self-Evolving Legal-Agent Framework
- Bayesian-Agent: Posterior-Guided Skill Evolution Across LLM Agent Harnesses
- Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks
- CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models
- Citation Grounding Measures the Oracle: Graph Coverage Determines Reported LLM Hallucination Rates in Law
- Large Language Models Meet Legal Artificial Intelligence: A Survey
- Overview of CAIL2018: Legal Judgment Prediction Competition
- From Question Answering to Task Completion: A Survey on Agent System and Harness Design
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems