Legal outcome prediction must disentangle objective case facts from adjudicative context. Merit-based rulings rely on factual evidence while technical disposals may hinge on judicial discretion.
arXiv:2607. 04261v1 Announce Type: new Abstract: Current Legal Judgment Prediction (LJP) is constrained by its reliance on post-hoc judicial materials, increasing the likelihood that models perform retrospective classification rather than true forecasting.
The paper introduces JudgeBiasBench, a benchmark that systematically quantifies judgment biases in large language model (LLM)-based judges across four dimensions and 12 bias types. It evaluates both generative and discriminative judges, revealing significant bias patterns that undermine reliability. The authors propose bias-aware training—reinforcement learning for generative judges and contrastive learning for discriminative judges—to reduce these biases while maintaining evaluation performance.
arXiv:2605. 29738v2 Announce Type: replace-cross Abstract: Legal NLP benchmarks overwhelmingly evaluate a single language or aggregate tasks that differ fundamentally across jurisdictions, making cross-lingual comparison impossible.
arXiv:2606. 06679v1 Announce Type: cross Abstract: Court judgments are central to legal practice and jurisprudence, yet discourse analysis of Hong Kong judgments has received limited attention, owing largely to the absence of expert-annotated corpora.
arXiv:2609.40103v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as automated judges for AI-generated content, yet a single judge is unreliable and even a panel...
The paper introduces Juris Policy Optimization (JPO), a post‑training framework designed to enhance structured legal reasoning in Chinese criminal judgment prediction. JPO first trains models with teacher‑generated rationales to guide a four‑step reasoning process, then applies reinforcement learning using a composite reward that balances prediction accuracy, reasoning completeness, and cross‑step consistency. Experiments on several open‑source language models and three Chinese legal benchmarks demonstrate that JPO consistently outperforms both supervised fine‑tuning and standard reinforcement learning baselines in terms of judgment prediction and reasoning quality.
The paper investigates how large language models (LLMs) used as judges in absolute scoring tasks exhibit systematic biases that compromise reliability. It shows that a judge’s task accuracy strongly predicts both its judging accuracy and its directional bias, yet more capable examinee models consistently receive more lenient judgments. To mitigate these biases, the authors propose a calibrated weighted majority voting (WMV) ensemble that estimates judges’ error rates from inter-judge agreement patterns, achieving near-oracle performance without labeled data and improving both accuracy and fairness.
arXiv:2606. 05644v1 Announce Type: new Abstract: When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of retrieval augmentation.
The paper introduces OBJECTION, an inference-time pipeline that adds an Adversarial Lawyer Agent to each of the three reasoning steps—offense, unlawfulness, and culpability—in legal judgment prediction models. By actively injecting defense arguments, the agent challenges the model’s default assumption of guilt, which is common in datasets biased toward guilty outcomes. Using a new Natural Innocent dataset of 3.4k real cases, OBJECTION reduces the False Guilty Rate from 82.93% to 16.69%, demonstrating significant improvement in substantive legal reasoning.
arXiv:2603. 00546v2 Announce Type: replace Abstract: Using Multimodal Large Language Models (MLLMs) as judges to achieve precise and consistent evaluations has gradually become an emerging paradigm across various domains.
arXiv:2608.29168v1 Announce Type: new Abstract: The LLM-as-a-Judge paradigm has emerged as a scalable alternative to human evaluation. However, single-model judges are limited by their inherent model...
The paper introduces Tasks over Application Manuals (TAM), a benchmark designed to test long‑horizon procedural reasoning in large language models. TAM uses real‑world tasks from ICD‑10‑CM clinical coding and U.S. federal sentencing, requiring models to follow extensive, rule‑based manuals and perform interdependent steps to produce exact answers. Experiments with GPT‑5 and various prompting strategies show very low exact‑match accuracy—1% for coding and 15.5% for sentencing—highlighting a gap between current benchmarks and the ability to reliably follow complex procedures.