Terminators: Terms of Service Parsing and Auditing Agents

TL;DR

Terminators is a modular framework using large language models to parse, verify, and audit Terms of Service documents, improving transparency and enforceability of complex legal texts.

Contribution

It introduces a novel, interpretable, agent-based approach to breaking down ToS parsing into three steps, enhancing auditability and reducing hallucinations in LLM outputs.

Findings

Effective parsing and auditing of OpenAI ToS with GPT-4o.

Structured LLM workflows improve transparency of legal documents.

Method promotes ethical use and regulatory oversight of web content.

Abstract

Terms of Service (ToS) documents are often lengthy and written in complex legal language, making them difficult for users to read and understand. To address this challenge, we propose Terminators, a modular agentic framework that leverages large language models (LLMs) to parse and audit ToS documents. Rather than treating ToS understanding as a black-box summarization problem, Terminators breaks the task down to three interpretable steps: term extraction, verification, and accountability planning. We demonstrate the effectiveness of our method on the OpenAI ToS using GPT-4o, highlighting strategies to minimize hallucinations and maximize auditability. Our results suggest that structured, agent-based LLM workflows can enhance both the usability and enforceability of complex legal documents. By translating opaque terms into actionable, verifiable components, Terminators promotes ethical use of web content by enabling greater transparency, empowering users to understand their digital rights, and supporting automated policy audits for regulatory or civic oversight.