Multimodal LLM-Driven Forensic Framework for Criminal Intent Detection in Chat Histories

This paper proposes a multimodal forensic framework that processes audio, text, and image or video captions from suspected chats. Chat history play vital role in criminal case analysis to capture the hidden intent and slang of the people. Using the graph constructor model, we extract the entities involved in the discussion for building a social graph by identifying key influencers and the flow of discussion. A large language model analyzes the generated graphs to identify behavioral insights, motives, and individual influences on the discussion. A structured forensic report is generated to uncover the hidden intent, suspicious terms, and rank the influencers and key entities with confidence scores to support the investigators. Experimental analysis demonstrates that the generated final report is more accurate for the conclusion of the chat history.