The paper presents an LLM-based pipeline for extracting structured data from criminal court decisions, using attribute exploration, text span extraction, and value normalization guided by expert-refinable annotation instructions. Evaluated on DUI and DDB traffic offenses, refining instructions improved extraction accuracy from 52% to 70% for DUI and increased annotator agreement. The study highlights that model consistency does not guarantee correctness and that disagreements can uncover ambiguous instructions.
arXiv:2503.00128v2 Announce Type: replace Abstract: Language models offer a way to scale costly, labour-intensive expert annotation, but their ability to reproduce expert judgements remains uncertain...
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 introduces the Profiling, Investigation, and Judgment (PIJ) benchmark, which contains 2,500 real homicide cases from five countries to evaluate large language models (LLMs) on pre‑arrest criminal investigation tasks. It assesses LLMs across criminal profiling, crime process reconstruction, and sentence prediction, revealing that performance drops as tasks require more implicit reasoning about unknown suspect profiles. The study finds that LLMs lag behind human experts, especially in inferential categories like motivation and victim‑offender relationships, and exhibit biases in gender, age, and motive attribution.
The paper evaluates legal text classification models for Korean sexual offense cases, comparing traditional machine learning, large language models, and fine‑tuned domain models. Fine‑tuned KLUE‑BERT achieved the highest accuracy of 99.3%, outperforming GPT‑3.5, GPT‑4.0, and other traditional approaches. Explainable AI techniques were used to analyze predictions, revealing linguistic features that influence decisions and highlighting limitations in capturing subtle textual cues, especially in real‑world KICS data.
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. 02150v2 Announce Type: replace-cross Abstract: The extraction of critical information from crime-related documents is a crucial task for law enforcement agencies.
The paper introduces the Profiling, Investigation, and Judgment (PIJ) benchmark, which contains 2,500 real homicide cases from five countries to evaluate large language models (LLMs) on pre‑arrest criminal investigation tasks. It assesses LLMs across criminal profiling, crime process reconstruction, and sentence prediction, revealing that performance drops as tasks require more implicit reasoning about unknown suspect profiles. The study finds that LLMs lag behind human experts, especially on inferential tasks like motivation and victim‑offender relationships, and exhibit biases in gender, age, and motive attribution.
arXiv:2603.02150v3 Announce Type: replace-cross Abstract: The extraction of critical information from crime-related documents is a crucial task for law enforcement agencies. The extraction of this in...
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:2608. 08830v1 Announce Type: new Abstract: Legal Statute Prediction (LSP) involves automatically identifying relevant legal statutes given factual descriptions in legal documents, typically framed as a multi-label classification task within natural language processing and information retrieval research.
The paper introduces a multi‑task pre‑training strategy for German traffic law that integrates Knowledge Graph (KG) information through Next Sentence Prediction, KG‑Guided Clustering, and KG‑Aware Paragraph Classification. By embedding structured legal knowledge into Transformer weights, the model can perform zero‑shot legal reasoning without explicit graph traversal. Experiments on nine encoders and 324 runs show substantial gains—up to 155% over baselines on synthetic StVO QA and improved performance on four of seven LexGLUE benchmarks, with consistent zero‑shot transfer to Austrian driving regulations.
The paper surveys how large language models (LLMs) are being applied in legal tasks such as judgement prediction, document analysis, and drafting. It reviews the benefits of automation while highlighting legal challenges like privacy, bias, and explainability. The authors also discuss data resources for legal domain specialization and outline future research directions.