2026-09-19T04:30:23Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1637222025-11-18T06:27:53Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Balakrishnan, Hari
Alizadeh, Mohammad
Noorbakhsh, Kimia
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2025-11-17T19:09:23Z
2025-11-17T19:09:23Z
2025-05
2025-08-14T19:32:27.069Z
https://hdl.handle.net/1721.1/163722
Assessing and enhancing human learning through question-answering is vital, especially when dealing with large documents, yet automating this process remains challenging. While large language models (LLMs) excel at summarization and answering queries, their ability to generate meaningful questions from lengthy texts remains underexplored. We propose Savaal, a scalable question-generation system with three objectives: (i) scalability, enabling question-generation from hundreds of pages of text (ii) depth of understanding, producing questions beyond factual recall to test conceptual reasoning, and (iii) domainindependence, automatically generating questions across diverse knowledge areas. Instead of providing an LLM with large documents as context, Savaal improves results with a threestage processing pipeline. Our evaluation with 76 human experts on 71 papers and PhD dissertations shows that Savaal generates questions that better test depth of understanding by 6.5× for dissertations and 1.5× for papers compared to a direct-prompting LLM baseline. Notably, as document length increases, Savaal’s advantages in higher question quality and lower cost become more pronounced.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Scaling Automatic Question Generation to Large Documents: A Concept-Driven Approach
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="ece54859-8572-4c3c-9615-825ae56bcbb1">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Scaling Automatic Question Generation to Large Documents: A Concept-Driven Approach</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Noorbakhsh, Kimia</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Assessing and enhancing human learning through question-answering is vital, especially when dealing with large documents, yet automating this process remains challenging. While large language models (LLMs) excel at summarization and answering queries, their ability to generate meaningful questions from lengthy texts remains underexplored. We propose Savaal, a scalable question-generation system with three objectives: (i) scalability, enabling question-generation from hundreds of pages of text (ii) depth of understanding, producing questions beyond factual recall to test conceptual reasoning, and (iii) domainindependence, automatically generating questions across diverse knowledge areas. Instead of providing an LLM with large documents as context, Savaal improves results with a threestage processing pipeline. Our evaluation with 76 human experts on 71 papers and PhD dissertations shows that Savaal generates questions that better test depth of understanding by 6.5× for dissertations and 1.5× for papers compared to a direct-prompting LLM baseline. Notably, as document length increases, Savaal’s advantages in higher question quality and lower cost become more pronounced.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>