arXiv AI
CrimeNER: Curated Dataset and Methods for Research and Investigation in Language Intelligence
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 9
Named-Entity Recognition in the Crime Domain (CrimeNER): Case Study and Dataset
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 AI
Jul 17
CrimeNER Demo: Named-Entity Recognition in the Crime Domain
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 AI
Jun 19
FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs
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.
arXiv Computation and Language
3d ago
Unlocking Criminal Court Decisions: Flexible Information Extraction for Empirical Legal Research
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 AI
Sep 23
IntLawNER: A Named Entity Recognition Dataset and Benchmark in International Law
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...
Hugging Face Trending Papers
Sep 17
Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence
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.