{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/119304"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/119304","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Can an LLM find its way around a Spreadsheet?","abstract":"Spreadsheets are routinely used in business and scientific contexts, and one of the most vexing challenges data analysts face is performing data cleaning prior to analysis and evaluation. The ad-hoc and arbitrary nature of data cleaning problems, such as typos, inconsistent formatting, missing values, and a lack of standardization, often creates the need for highly specialized pipelines. We ask whether an LLM can find its way around a spreadsheet and how to support end-users in taking their free-form data processing requests to fruition. Just like RAG retrieves context to answer users' queries, we demonstrate how we can retrieve elements from a code library to compose data processing pipelines. Through comprehensive experiments, we demonstrate the quality of our system and how it is able to continuously augment its vocabulary by saving new codes and pipelines back to the code library for future retrieval.","abstract_html":"Spreadsheets are routinely used in business and scientific contexts, and one of the most vexing challenges data analysts face is performing data cleaning prior to analysis and evaluation. The ad-hoc and arbitrary nature of data cleaning problems, such as typos, inconsistent formatting, missing values, and a lack of standardization, often creates the need for highly specialized pipelines. We ask whether an LLM can find its way around a spreadsheet and how to support end-users in taking their free-form data processing requests to fruition. Just like RAG retrieves context to answer users' queries, we demonstrate how we can retrieve elements from a code library to compose data processing pipelines. Through comprehensive experiments, we demonstrate the quality of our system and how it is able to continuously augment its vocabulary by saving new codes and pipelines back to the code library for future retrieval.","abstract_has_math":false,"creators":["Lee, Cho Ting"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science & Applications","degree_department":"Computer Science and#38; Applications","school":null,"contributors":[],"advisors":[],"committee_chairs":["Ramakrishnan, Narendran"],"committee_members":["Simeone, John","Lu, Chang Tien"],"year":2024,"date_issued":"2024-06-05","date_published":"2024-06-05","updated_at":"2026-07-22T22:19:15Z","subjects":["LLMs","data cleaning","end-user programming"],"languages":["en"],"rights":["Creative Commons Attribution 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:40725"],"render_values":[{"text":"vt_gsexam:40725","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/119304","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Ramakrishnan, Narendran"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Simeone, John","Lu, Chang Tien"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science and#38; Applications"]},{"key":"dc:creator","label":"Author","values":["Lee, Cho Ting"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-06-06T08:00:51Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-06-06T08:00:51Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-06-05"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science & Applications"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["LLMs","data cleaning","end-user programming"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Creative Commons Attribution 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:40725"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/119304"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Spreadsheets are routinely used in business and scientific contexts, and one of the most vexing challenges data analysts face is performing data cleaning prior to analysis and evaluation. The ad-hoc and arbitrary nature of data cleaning problems, such as typos, inconsistent formatting, missing values, and a lack of standardization, often creates the need for highly specialized pipelines. We ask whether an LLM can find its way around a spreadsheet and how to support end-users in taking their free-form data processing requests to fruition. Just like RAG retrieves context to answer users' queries, we demonstrate how we can retrieve elements from a code library to compose data processing pipelines. Through comprehensive experiments, we demonstrate the quality of our system and how it is able to continuously augment its vocabulary by saving new codes and pipelines back to the code library for future retrieval."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Spreadsheets are frequently utilized in both business and scientific settings, and one of the most challenging tasks that must be accomplished before analysis and evaluation can take place is the cleansing of the data. The ad-hoc and arbitrary nature of issues in data quality, such as typos, inconsistent formatting, missing values, and lack of standardization, often creates the need for highly specialized data cleaning pipelines. Within the scope of this thesis, we investigate whether a large language model (LLM) can navigate its way around a spreadsheet, as well as how to assist end-users in bringing their free-form data processing requests to fruition. Just like Retrieval-Augmented Generation (RAG) retrieves context to answer user queries, we demonstrate how we can retrieve elements from a Python code reference to compose data processing pipelines. Through comprehensive experiments, we showcase the quality of our system and how it is capable of continuously improving its code-writing ability by saving new codes and pipelines back to the code library for future retrieval."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Can an LLM find its way around a Spreadsheet?"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Ramakrishnan, Narendran"],"dc:contributor.committeemember":["Simeone, John","Lu, Chang Tien"],"dc:contributor.department":["Computer Science and#38; Applications"],"dc:creator":["Lee, Cho Ting"],"dc:date.accessioned":["2024-06-06T08:00:51Z"],"dc:date.available":["2024-06-06T08:00:51Z"],"dc:date.issued":["2024-06-05"],"dc:description.abstract":["Spreadsheets are routinely used in business and scientific contexts, and one of the most vexing challenges data analysts face is performing data cleaning prior to analysis and evaluation. The ad-hoc and arbitrary nature of data cleaning problems, such as typos, inconsistent formatting, missing values, and a lack of standardization, often creates the need for highly specialized pipelines. We ask whether an LLM can find its way around a spreadsheet and how to support end-users in taking their free-form data processing requests to fruition. Just like RAG retrieves context to answer users' queries, we demonstrate how we can retrieve elements from a code library to compose data processing pipelines. Through comprehensive experiments, we demonstrate the quality of our system and how it is able to continuously augment its vocabulary by saving new codes and pipelines back to the code library for future retrieval."],"dc:description.abstractgeneral":["Spreadsheets are frequently utilized in both business and scientific settings, and one of the most challenging tasks that must be accomplished before analysis and evaluation can take place is the cleansing of the data. The ad-hoc and arbitrary nature of issues in data quality, such as typos, inconsistent formatting, missing values, and lack of standardization, often creates the need for highly specialized data cleaning pipelines. Within the scope of this thesis, we investigate whether a large language model (LLM) can navigate its way around a spreadsheet, as well as how to assist end-users in bringing their free-form data processing requests to fruition. Just like Retrieval-Augmented Generation (RAG) retrieves context to answer user queries, we demonstrate how we can retrieve elements from a Python code reference to compose data processing pipelines. Through comprehensive experiments, we showcase the quality of our system and how it is capable of continuously improving its code-writing ability by saving new codes and pipelines back to the code library for future retrieval."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:40725"],"dc:identifier.uri":["https://hdl.handle.net/10919/119304"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["Creative Commons Attribution 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by/4.0/"],"dc:subject":["LLMs","data cleaning","end-user programming"],"dc:title":["Can an LLM find its way around a Spreadsheet?"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science & Applications"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:15Z"}