{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/156764"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/156764","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"SAGE: Segmenting and Grouping Data Effectively using Large Language Models","abstract":"Grouping is a technique used to organize data into manageable pieces, reducing cognitive load and enabling users to focus on discovering higher-level insights and generating new questions. However, creating groups remains a challenge, often requiring users to have prior domain knowledge or an understanding of the underlying structure of the data. We introduce SAGE, a novel technique that leverages the knowledge base and pattern recognition abilities of large language models (LLMs) to segment and group data with domainawareness. We instantiate our technique through two structures: bins and highlights; bins are contiguous, non-overlapping ranges that segment a single field into groups; highlights are multi-field intersections of ranges that surface broader groups in the data. We integrate these structures into Olli, an open-source tool that converts data visualizations into accessible, keyboard-navigable textual formats to facilitate a study with 15 blind and low-vision (BLV) participants, recognizing them as experts in assessing agency. Through this study, we evaluate how SAGE impacts a user’s interpretation of data and visualizations, and find our technique provides a rich contextual framework for users to independently scaffold their initial sensemaking process.","abstract_html":"Grouping is a technique used to organize data into manageable pieces, reducing cognitive load and enabling users to focus on discovering higher-level insights and generating new questions. However, creating groups remains a challenge, often requiring users to have prior domain knowledge or an understanding of the underlying structure of the data. We introduce SAGE, a novel technique that leverages the knowledge base and pattern recognition abilities of large language models (LLMs) to segment and group data with domainawareness. We instantiate our technique through two structures: bins and highlights; bins are contiguous, non-overlapping ranges that segment a single field into groups; highlights are multi-field intersections of ranges that surface broader groups in the data. We integrate these structures into Olli, an open-source tool that converts data visualizations into accessible, keyboard-navigable textual formats to facilitate a study with 15 blind and low-vision (BLV) participants, recognizing them as experts in assessing agency. Through this study, we evaluate how SAGE impacts a user’s interpretation of data and visualizations, and find our technique provides a rich contextual framework for users to independently scaffold their initial sensemaking process.","abstract_has_math":false,"creators":["Pedraza Pineros, Isabella"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Satyanarayan, Arvind"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:20:54Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/156764","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Satyanarayan, Arvind"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Pedraza Pineros, Isabella"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-16T13:47:42Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-09-16T13:47:42Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/156764"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Grouping is a technique used to organize data into manageable pieces, reducing cognitive load and enabling users to focus on discovering higher-level insights and generating new questions. However, creating groups remains a challenge, often requiring users to have prior domain knowledge or an understanding of the underlying structure of the data. We introduce SAGE, a novel technique that leverages the knowledge base and pattern recognition abilities of large language models (LLMs) to segment and group data with domainawareness. We instantiate our technique through two structures: bins and highlights; bins are contiguous, non-overlapping ranges that segment a single field into groups; highlights are multi-field intersections of ranges that surface broader groups in the data. We integrate these structures into Olli, an open-source tool that converts data visualizations into accessible, keyboard-navigable textual formats to facilitate a study with 15 blind and low-vision (BLV) participants, recognizing them as experts in assessing agency. Through this study, we evaluate how SAGE impacts a user’s interpretation of data and visualizations, and find our technique provides a rich contextual framework for users to independently scaffold their initial sensemaking process."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["SAGE: Segmenting and Grouping Data Effectively using Large Language Models"]}]}],"canonical_facts":{"dc:contributor.advisor":["Satyanarayan, Arvind"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Pedraza Pineros, Isabella"],"dc:date.accessioned":["2024-09-16T13:47:42Z"],"dc:date.available":["2024-09-16T13:47:42Z"],"dc:date.issued":["2024-05"],"dc:description.abstract":["Grouping is a technique used to organize data into manageable pieces, reducing cognitive load and enabling users to focus on discovering higher-level insights and generating new questions. However, creating groups remains a challenge, often requiring users to have prior domain knowledge or an understanding of the underlying structure of the data. We introduce SAGE, a novel technique that leverages the knowledge base and pattern recognition abilities of large language models (LLMs) to segment and group data with domainawareness. We instantiate our technique through two structures: bins and highlights; bins are contiguous, non-overlapping ranges that segment a single field into groups; highlights are multi-field intersections of ranges that surface broader groups in the data. We integrate these structures into Olli, an open-source tool that converts data visualizations into accessible, keyboard-navigable textual formats to facilitate a study with 15 blind and low-vision (BLV) participants, recognizing them as experts in assessing agency. Through this study, we evaluate how SAGE impacts a user’s interpretation of data and visualizations, and find our technique provides a rich contextual framework for users to independently scaffold their initial sensemaking process."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/156764"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["SAGE: Segmenting and Grouping Data Effectively using Large Language Models"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:20:54Z"}