Can LLMs Create Legally Relevant Summaries and Analyses of Videos?

2025-11-15

AI Summary

This study investigates the capability of large language models (LLMs) to directly comprehend legal events from raw video inputs and generate legally coherent summaries and formal correspondence—thereby lowering barriers to legal expression for laypersons in insurance claims, litigation, and similar contexts, and enhancing judicial accessibility. We propose the first end-to-end video-to-legal-text generation framework, circumventing the conventional reliance on manually transcribed or annotated textual inputs. Our approach integrates multimodal video understanding with domain-specific legal language generation, evaluated on a curated dataset of 120 authentic YouTube videos depicting real-world legal incidents. Human evaluation confirms that 71.7% of automatically generated summaries meet high or medium quality standards, demonstrating the feasibility of LLMs to extract factual legal content and produce formal legal documents without human paraphrasing. The core contribution is the establishment of a video-driven paradigm for legal assistance, providing empirical validation and methodological foundations for inclusive, accessible legal technology.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Video Understanding & Activity Analysis
• Natural Language Processing: (Large) Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Understanding the legally relevant factual basis of an event and conveying it through text is a key skill of legal professionals. This skill is important for preparing forms (e.g., insurance claims) or other legal documents (e.g., court claims), but often presents a challenge for laypeople. Current AI approaches aim to bridge this gap, but mostly rely on the user to articulate what has happened in text, which may be challenging for many. Here, we investigate the capability of large language models (LLMs) to understand and summarize events occurring in videos. We ask an LLM to summarize and draft legal letters, based on 120 YouTube videos showing legal issues in various domains. Overall, 71.7% of the summaries were rated as of high or medium quality, which is a promising result, opening the door to a number of applications in e.g. access to justice.

Problem

• Evaluating LLMs' ability to summarize legally relevant video content
• Assessing automated generation of legal documents from video evidence
• Bridging the justice gap through AI-powered video analysis systems

Innovation

• LLMs summarize videos for legal document preparation
• LLMs draft legal letters based on YouTube video content
• System achieves 71.7% high-medium quality legal summaries