HumSum: A Personalized Lecture Summarization Tool for Humanities Students Using LLMs

Zahra Kolagar, Alessandra Zarcone


Abstract
Generative AI systems aim to create customizable content for their users, with a subsequent surge in demand for adaptable tools that can create personalized experiences. This paper presents HumSum, a web-based tool tailored for humanities students to effectively summarize their lecture transcripts and to personalize the summaries to their specific needs. We first conducted a survey driven by different potential scenarios to collect user preferences to guide the implementation of this tool. Utilizing Streamlit, we crafted the user interface, while Langchain’s Map Reduce function facilitated the summarization process for extensive lectures using OpenAI’s GPT-4 model. HumSum is an intuitive tool serving various summarization needs, infusing personalization into the tool’s functionality without necessitating the collection of personal user data.
Anthology ID:
2024.personalize-1.4
Volume:
Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024)
Month:
March
Year:
2024
Address:
St. Julians, Malta
Editors:
Ameet Deshpande, EunJeong Hwang, Vishvak Murahari, Joon Sung Park, Diyi Yang, Ashish Sabharwal, Karthik Narasimhan, Ashwin Kalyan
Venues:
PERSONALIZE | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
36–70
Language:
URL:
https://aclanthology.org/2024.personalize-1.4
DOI:
Bibkey:
Cite (ACL):
Zahra Kolagar and Alessandra Zarcone. 2024. HumSum: A Personalized Lecture Summarization Tool for Humanities Students Using LLMs. In Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024), pages 36–70, St. Julians, Malta. Association for Computational Linguistics.
Cite (Informal):
HumSum: A Personalized Lecture Summarization Tool for Humanities Students Using LLMs (Kolagar & Zarcone, PERSONALIZE-WS 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.personalize-1.4.pdf