cs.CLNov 3, 2026

PROSE: Preservation-Constrained Selective Editing for Guilty Bias in Legal Judgment Prediction

Authors: Yimeng Wang, Zeyuan Tian, Xinyu Wang, Danyang Gao, Chenglei Shen, Zhongxiang Sun, Lei La, Weijie Yu

Organizations: School of Artificial Intelligence and Data Science, University of International Business and Economics · Department of Computer Science, University of Chicago · School of Law, University of International Business and Economics · Gaoling School of Artificial Intelligence, Renmin University of China

Abstract

Legal judgment prediction models may retain a guilty verdict after a legally decisive condition has been altered such that the specified charge is no longer established. We study this guilty bias via selective repair over matched charge-established and charge-not-established cases, where the unsupported verdict should change while its supported counterpart remains stable. We construct CAIL-MC, a legally reviewed dataset of 11,478 matched pairs covering 261 Chinese criminal charges. Held-out activation interventions show that contrasts learned from correctly resolved pairs transfer to false-guilty cases, but target-reaching interventions can also damage matched supported-guilty decisions. Motivated by this observation, we introduce PROSE, which reconstructs case-specific targets from a training-derived residual geometry, aligns them with a local margin-descent signal, attenuates supported-guilty-sensitive components, and realizes bounded targets through a preservation-regularized low-rank parameter update. Across Qwen3-8B and GLM4-9B, PROSE achieves stronger pairwise safe repair and evidence sensitivity, while preserving standard single-pass inference.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

May 27, 2026

The Cases LJP Never Sees: Prosecution Decision Prediction for More Complete Criminal Liability Assessment

Legal Judgment Prediction (LJP) has become a core benchmark for evaluating AI in the criminal legal domain, but it only sees criminal cases that have already passed prosecutorial review and been formally indicted. As a result, LJP leaves a substantial blind spot in assessing criminal liability, overlooking cases involving insufficient evidence, no criminal liability, or guilt exempted from punishment. To fill this gap, we propose Prosecution Decision Prediction (PDP), the first Legal AI task built around prosecutorial review, which classifies each case into prosecution or one of three non-prosecution decisions and reflects legal AI's capabilities in evidence evaluation, legal subsumption, and value-based discretion. We further construct PDP-Bench, a benchmark of 4{,}630 real Chinese prosecutorial decisions spanning 190 charges. Extensive experiments show that state-of-the-art LLMs perform substantially worse on PDP than on LJP and that mainstream enhancement routes fail to close the gap. Moreover, controlled RLVR interventions show that simple outcome rewards fail to produce generalizable PDP discrimination.
Aug 30, 2026

JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction

Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing outcomes from case facts. Unlike standard classification tasks, it involves a structured reasoning process in which statutes should be matched with facts, charges should be justified by statutes, and sentencing outcomes should remain consistent with charges. Existing approaches optimize final labels, and while some have attempted to evaluate reasoning quality, their evaluations are indirect, often relying on LLM-generated rubrics that reflect model-internal preferences rather than the inherent logical structure of legal adjudication. We propose Juris Policy Optimization (JPO), a post-training framework for structured legal reasoning in Chinese criminal judgment prediction. JPO first uses teacher-generated rationales to supervise a standardized four-step reasoning process, and then applies reinforcement learning with a composite reward over legal prediction quality, reasoning structure completeness, and cross-step consistency. JPO further introduces token-level advantage reweighting and adaptive clipping for legally salient reasoning segments. Experiments on multiple open-source language models and three Chinese legal benchmarks show that JPO consistently improves both judgment prediction and reasoning quality over supervised fine-tuning and reinforcement learning baselines.
Mar 12, 2026

LLM-Assisted Causal Structure Disambiguation and Factor Extraction for Legal Judgment Prediction

Mainstream methods for Legal Judgment Prediction (LJP) based on Pre-trained Language Models (PLMs) heavily rely on the statistical correlation between case facts and judgment results. This paradigm lacks explicit modeling of legal constituent elements and underlying causal logic, making models prone to learning spurious correlations and suffering from poor robustness. While introducing causal inference can mitigate this issue, existing causal LJP methods face two critical bottlenecks in real-world legal texts: inaccurate legal factor extraction with severe noise, and significant uncertainty in causal structure discovery due to Markov equivalence under sparse features. To address these challenges, we propose an enhanced causal inference framework that integrates Large Language Model (LLM) priors with statistical causal discovery. First, we design a coarse-to-fine hybrid extraction mechanism combining statistical sampling and LLM semantic reasoning to accurately identify and purify standard legal constituent elements. Second, to resolve structural uncertainty, we introduce an LLM-assisted causal structure disambiguation mechanism. By utilizing the LLM as a constrained prior knowledge base, we conduct probabilistic evaluation and pruning on ambiguous causal directions to generate legally compliant candidate causal graphs. Finally, a causal-aware judgment prediction model is constructed by explicitly constraining text attention intensity via the generated causal graphs. Extensive experiments on multiple benchmark datasets, including LEVEN , QA, and CAIL, demonstrate that our proposed method significantly outperforms state-of-the-art baselines in both predictive accuracy and robustness, particularly in distinguishing confusing charges.