LAPIS: Language Model-Augmented Police Investigation System
Not on the map. Why?
Abstract (arXiv)
Crime situations are race against time. An AI-assisted criminal investigation system, providing prompt but precise legal counsel is in need for police officers. We introduce LAPIS (Language Model Augmented Police Investigation System), an automated system that assists police officers to perform rational and legal investigative actions. We constructed a finetuning dataset and retrieval knowledgebase specialized in crime investigation legal reasoning task. We extended the dataset's quality by incorporating manual curation efforts done by a group of domain experts. We then finetuned the pretrained weights of a smaller Korean language model to the newly constructed dataset and integrated it with the crime investigation knowledgebase retrieval approach. Experimental results show LAPIS' potential in providing reliable legal guidance for police officers, even better than the proprietary GPT-4 model. Qualitative analysis on the rationales generated by LAPIS demonstrate the model's reasoning ability to leverage the premises and derive legally correct conclusions.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 17 of its 46 references that are in the map. First posted on arXiv 19 Jul 2024.
Builds on
17 of 46 references.
References · 17
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
- 2022Large Language Models Are Reasoning Teacherscited by 318
- 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 302
- 2022Teaching Small Language Models to Reasoncited by 279
- 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 278
- 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 144
- 2023Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Healthcited by 118
- 2023Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Taskscited by 62
- 2022Legal Prompting: Teaching a Language Model to Think Like a Lawyercited by 60
- 2022Legal Prompt Engineering for Multilingual Legal Judgement Predictioncited by 54
- 2023Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Predictioncited by 37
5 more
- 2023ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmarkcited by 33
- 2024Small Language Models Learn Enhanced Reasoning Skills from Medical Textbookscited by 30
- 2023Ethical ChatGPT: Concerns, Challenges, and Commandmentscited by 13
- 2023Beyond Logic Programming for Legal Reasoningcited by 4
- 2019A Bayesian Hierarchical Model for Criminal Investigationscited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning
- 2024Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justice
- 2025A Reasoning-Focused Legal Retrieval Benchmark
- 2026Legal Reasoning Is Not Lawyering: Rethinking Legal Benchmarks for Pro Se Access to Justice
- 2025Hey GPT-OSS, Looks Like You Got It -- Now Walk Me Through It! An Assessment of the Reasoning Language Models Chain of Thought Mechanism for Digital Forensics
- 2026Bridging the First-Hour Gap: Evaluating AI Reliability and Benchmarking Deficiencies in Cyber Incident Response for Law Enforcement ↗
- 2025Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond
- 2023DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services