VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction

• URL: http://arxiv.org/abs/2603.19306v1
• Date: Fri, 13 Mar 2026 07:19:08 GMT
• Title: VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction
• Abstract summary: Legal Judgment Prediction (LJP) predicts applicable law articles, charges, and penalty terms from case facts.<n>We propose VERDICT, a self-refining collaborative multi-agent framework that simulates a virtual collegial panel.
• Score: 37.517774304242444
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Legal Judgment Prediction (LJP) predicts applicable law articles, charges, and penalty terms from case facts. Beyond accuracy, LJP calls for intrinsically interpretable and legally grounded reasoning that can reconcile statutory rules with precedent-informed standards. However, existing methods often behave as static, one-shot predictors, providing limited procedural support for verifiable reasoning and little capability to adapt as jurisprudential practice evolves. We propose VERDICT, a self-refining collaborative multi-agent framework that simulates a virtual collegial panel. VERDICT assigns specialized agents to complementary roles (e.g., fact structuring, legal retrieval, opinion drafting, and supervisory verification) and coordinates them in a traceable draft--verify--revise workflow with explicit Pass/Reject feedback, producing verifiable reasoning traces and revision rationales. To capture evolving case experience, we further introduce a Hybrid Jurisprudential Memory (HJM) grounded in the Micro-Directive Paradigm, which stores precedent standards and continually distills validated multi-agent verification trajectories into updated Micro-Directives for continual learning across cases. We evaluate VERDICT on CAIL2018 and a newly constructed CJO2025 dataset with a strict future time-split for temporal generalization. VERDICT achieves state-of-the-art performance on CAIL2018 and demonstrates strong generalization on CJO2025. To facilitate reproducibility and further research, we release our code and the dataset at https://anonymous.4open.science/r/ARR-4437.

Related papers

• PROSLEX: A Novel Dataset for Expert-Annotated Legal Statute Prediction for Indian Judiciary [7.985120216055807]
  We present PROSLEX, a comprehensive dataset comprising 1,623 expert-annotated legal documents from the Indian context.<n>We evaluate various prompting strategies, including zero-shot, few-shot, chain-of-thought, and tree-of-thought, to generate both statute predictions and their corresponding legal rationales.<n>Our evaluation framework measures not only performance but also the coherence and legal validity of generated explanations, positioning PROSLEX as a benchmark for developing explainable AI systems.
  arXiv  Detail & Related papers  (2026-08-09T17:24:09Z)
• When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval [20.750798833808556]
  We propose a self-evolving framework for rule-driven query rewriting that enhances BM25 without any parameter training.<n>We evaluate our method on the Chinese legal case retrieval benchmark LeCaRD-v2.
  arXiv  Detail & Related papers  (2026-06-15T19:09:31Z)
• Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering [54.97384993676565]
  We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from complex national R&D regulations.<n>RefWalk traverses cross-document citations, fuses multi-view candidates via max-based aggregation, and enforces per-rule attribution to explicitly map claims to sources.
  arXiv  Detail & Related papers  (2026-05-28T10:38:38Z)
• Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization [30.089203895815384]
  Existing approaches, typically relying on standard Retrieval-Augmented Generation and Supervised Fine-Tuning, often suffer from insufficient evidence recall, hallucinated statutory references, and flawed legal reasoning.<n>We propose Judge-R1, a unified framework designed to logically enhance LLM-based judgment document generation by jointly improving legal information collection and judgment document generation.<n>Experiments on the JuDGE benchmark demonstrate that Judge-R1 significantly outperforms state-of-the-art baselines in both legal accuracy and generation quality.
  arXiv  Detail & Related papers  (2026-05-03T18:32:10Z)
• LawThinker: A Deep Research Legal Agent in Dynamic Environments [51.782293183431676]
  LawThinker is an autonomous legal research agent.<n>It enforces verification as an atomic operation after every knowledge exploration step.<n>LawThinker achieves a 24% improvement over direct reasoning.
  arXiv  Detail & Related papers  (2026-02-12T15:19:11Z)
• LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [54.57434222018289]
  We present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain.<n>LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning.<n>We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI.
  arXiv  Detail & Related papers  (2026-01-31T10:18:32Z)
• AR-BENCH: Benchmarking Legal Reasoning with Judgment Error Detection, Classification and Correction [30.1142279338937]
  Legal judgments may contain errors due to the complexity of case circumstances and the abstract nature of legal concepts.<n>Current legal AI research focuses on tasks like judgment prediction and legal document generation.<n>We introduce a novel task APPELLATE REVIEW, aiming to assess models' diagnostic reasoning and reliability in legal practice.
  arXiv  Detail & Related papers  (2026-01-30T09:22:32Z)
• Preventing the Collapse of Peer Review Requires Verification-First AI [49.995126139461085]
  We propose truth-coupling, i.e. how tightly venue scores track latent scientific truth.<n>We formalize two forces that drive a phase transition toward proxy-sovereign evaluation.
  arXiv  Detail & Related papers  (2026-01-23T17:17:32Z)
• AppellateGen: A Benchmark for Appellate Legal Judgment Generation [30.9030336647868]
  We introduce AppellateGen, a benchmark for second-instance legal judgment generation comprising 7,351 case pairs.<n>The task requires models to draft legally binding judgments by reasoning over the initial verdict and evidentiary updates.<n>We propose a judicial Standard Operating Procedure (SOP)-based Legal Multi-Agent System (SLMAS) to simulate judicial, which decomposes the generation process into discrete stages of issue identification, retrieval, and drafting.
  arXiv  Detail & Related papers  (2026-01-04T02:15:17Z)
• Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics [30.232667436008978]
  We present a hybrid legal QA agent tailored for judicial settings.<n>It integrates retrieval-augmented generation (RAG) with multi-model ensembling to deliver reliable, auditable, and continuously updatable counsel.
  arXiv  Detail & Related papers  (2025-11-03T15:30:58Z)
• RLJP: Legal Judgment Prediction via First-Order Logic Rule-enhanced with Large Language Models [58.69183479148083]
  Legal Judgment Prediction (LJP) is a pivotal task in legal AI.<n>Existing LJP models integrate judicial precedents and legal knowledge for high performance.<n>But they neglect legal reasoning logic, a critical component of legal judgments requiring rigorous logical analysis.<n>This paper proposes a rule-enhanced legal judgment prediction framework based on first-order logic (FOL) formalism and comparative learning (CL)
  arXiv  Detail & Related papers  (2025-05-27T14:50:21Z)
• ECtHR-PCR: A Dataset for Precedent Understanding and Prior Case Retrieval in the European Court of Human Rights [1.3723120574076126]
  We develop a prior case retrieval dataset based on judgements from the European Court of Human Rights (ECtHR) We benchmark different lexical and dense retrieval approaches with various negative sampling strategies. We find that difficulty-based negative sampling strategies were not effective for the PCR task.
  arXiv  Detail & Related papers  (2024-03-31T08:06:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.