LAPIS: Language Model-Augmented Police Investigation System

TL;DR

LAPIS is an AI system that assists police in legal reasoning during investigations by combining a fine-tuned Korean language model with a specialized knowledgebase, outperforming GPT-4 in providing legal guidance.

Contribution

The paper introduces a novel AI-assisted investigation system that integrates a fine-tuned Korean language model with a domain-specific knowledgebase for legal reasoning.

Findings

LAPIS provides reliable legal guidance surpassing GPT-4.

The system demonstrates strong reasoning ability with legally correct conclusions.

Manual curation improves dataset quality and system performance.

Abstract

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.