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.
arXiv:2607. 14800v1 Announce Type: new Abstract: We present CrimeNER Demo, an AI-powered platform that enables us to extract general crime-related information from documents and classify them into entity types with two levels of granularity.
arXiv:2606. 19710v1 Announce Type: cross Abstract: Court proceedings contain valuable evidence about human smuggling networks, but this information is often buried within unstructured, jargon-heavy legal documents.
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:2609.22529v1 Announce Type: new Abstract: International law provides the normative framework through which states coordinate action, regulate armed conflict, and protect human rights, yet its t...
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 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.
The paper introduces a weakly supervised framework for extracting dataset mentions from forced displacement and Fragile, Conflict, and Violence (FCV) documents. It uses a lightweight model trained on general research literature to generate candidate mentions, which are then refined by a large language model that validates or rejects them and corrects boundaries. The refined annotations are augmented with synthetic and contrastive examples to fine‑tune the model, achieving 74.1% precision and 70.5% recall on a benchmark of 1,706 passages, with higher precision (89.5%) on passages that contain dataset references.
Large language models are candidates for collecting and analyzing records in criminal investigations and mass surveillance. Their capability and accuracy in this work cannot currently be measured. Rea...
arXiv:2606. 08376v1 Announce Type: cross Abstract: As artificial intelligence (AI) systems are increasingly deployed across socially consequential domains, reports of AI-related harms and failures have grown in frequency and diversity.
arXiv:2604. 04790v2 Announce Type: replace-cross Abstract: Natural language processing (NLP) advances have powered a generation of LegalTech systems, but Turkish law remains under-served by domain-specific data and models.
The paper introduces a scalable, multi-step framework designed to improve the quality of Named Entity Recognition (NER) annotations, particularly in low-resource languages. It employs a frequency-based iterative approach that combines self‑training with a dual‑threshold mechanism to increase inference confidence. Experiments on various NER datasets show notable performance gains over the original data, and the study also investigates the use of generative Large Language Models for NER tasks.