Abstract
Many internet websites and online services have associated terms of service that a user needs to agree with prior to using the website. Such terms of service are often written in dense legalese and are difficult for users to read. Thus, a common behavior is for the user to accept the terms of service without reading them. This disclosure describes the use of a large language model (LLM) or other suitable text summarization technique to generate a summary of such terms of service. When a user visits a website or online service, the presence of a terms of service document is automatically detected. Upon detection, the text is analyzed using a LLM and a user-readable summary of shorter length is provided to the user.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Azose, Benjamin, "Generating Website Terms of Service Summary Using a Large Language Model", Technical Disclosure Commons, (August 02, 2023)
https://www.tdcommons.org/dpubs_series/6107