Abstract
A system is disclosed that provides a summary of web-based content. Web-based content comprising text-based content is received by a browser. A portion of the text-based content is processed through a large language model to determine a summary of the portion of the text-based content. The portion is determined according to a threshold token limit. The summary is provided for display via a user interface.
Implementations of the present disclosure are generally directed to user device generation of a summary of web-based content (webpages, text, images, media files, etc.) via a generative model, such as a large language model (LLM). The large language model can be fine-tuned via a process that reduces the number of model parameters that can be changed during fine tuning. In some examples, the content summary is appended to a link when a user shares the link. In some examples, the content summary is provided via a tab resumption card that includes information related to a previously viewed link.
It is appreciated that methods in accordance with the present disclosure can include any combination of the aspects and features described herein. That is, methods in accordance with the present disclosure are not limited to the combinations of aspects and features specifically described herein but also may include any combination of the aspects and features provided.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Boonsiri, Thomas Nont; Sivakumar, Siddhartha; Ramos, Salvador Guerrero; Liang, Lan Julia; and Martinez, Elizabeth, "Summarization Framework for Sharing and Contextual Previews", Technical Disclosure Commons, (April 03, 2025)
https://www.tdcommons.org/dpubs_series/7969