SUMMPILOT: Bridging Efficiency and Customization for Interactive Summarization System

TL;DR

SummPilot is an interactive summarization system that combines automatic and personalized summaries using large language models, enabling user engagement through semantic graphs, entity clustering, and explainability.

Contribution

The paper introduces SummPilot, a novel system that integrates automatic and interactive summarization for personalized content generation using large language models.

Findings

Demonstrates SummPilot's adaptability through user studies

Shows effectiveness of interactive components like semantic graphs

Validates usefulness for personalized summarization

Abstract

This paper incorporates the efficiency of automatic summarization and addresses the challenge of generating personalized summaries tailored to individual users' interests and requirements. To tackle this challenge, we introduce SummPilot, an interaction-based customizable summarization system. SummPilot leverages a large language model to facilitate both automatic and interactive summarization. Users can engage with the system to understand document content and personalize summaries through interactive components such as semantic graphs, entity clustering, and explainable evaluation. Our demo and user studies demonstrate SummPilot's adaptability and usefulness for customizable summarization.