{"id":{"repo_id":"utc","oai_identifier":"oai:scholar.utc.edu:theses-2221"},"canonical_url":"https://search.dev.ndltd.org/etd/utc/oai:scholar.utc.edu:theses-2221","repository":{"repo_id":"utc","name":"University of Tennessee - Chattanooga","base_url":"https://scholar.utc.edu/do/oai/"},"display":{"title":"A question to query LLM as a pipeline replacement in knowledge graph question answering systems","abstract":"Knowledge Graph Question Answering (KGQA) pipelines commonly depend on separate entity and relation predictors before querying the graph, which introduces engineering complexity and costly inference passes over large vocabularies. This thesis presents a drop-in replacement for those modules: a fine-tuned large language model (LLM) that translates a natural-language question directly into an executable SPARQL query. We fine-tune instruction-tuned backbones, Llama-3.1-8B-Instruct and Mistral-7B-Instruct, on paired (question, gold SPARQL) examples, which are formatted through chat templates. As a result, the models can perform single-step query generation. The training and inference pipeline includes a lightweight post-processor that corrects tokenizer-induced spacing artifacts in generated SPARQL, improving exact-match robustness without altering query structure. On a held-out test set, the fine-tuned models achieve 97.9% (Llama) and 94.0% (Mistral) exact-match accuracy for natural-language-to-SPARQL generation, demonstrating that an end-to-end translator can meet or exceed the accuracy of typical multi-module KGQA stacks while substantially simplifying the architecture.","abstract_html":"Knowledge Graph Question Answering (KGQA) pipelines commonly depend on separate entity and relation predictors before querying the graph, which introduces engineering complexity and costly inference passes over large vocabularies. This thesis presents a drop-in replacement for those modules: a fine-tuned large language model (LLM) that translates a natural-language question directly into an executable SPARQL query. We fine-tune instruction-tuned backbones, Llama-3.1-8B-Instruct and Mistral-7B-Instruct, on paired (question, gold SPARQL) examples, which are formatted through chat templates. As a result, the models can perform single-step query generation. The training and inference pipeline includes a lightweight post-processor that corrects tokenizer-induced spacing artifacts in generated SPARQL, improving exact-match robustness without altering query structure. On a held-out test set, the fine-tuned models achieve 97.9% (Llama) and 94.0% (Mistral) exact-match accuracy for natural-language-to-SPARQL generation, demonstrating that an end-to-end translator can meet or exceed the accuracy of typical multi-module KGQA stacks while substantially simplifying the architecture.","abstract_has_math":false,"creators":["Schwartz, Major"],"institution":"University of Tennessee at Chattanooga","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Xie, Mengjun","Sakib, Shahnewaz Karim; Liang, Yu","College of Engineering and Computer Science"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-07-24T05:47:28Z","subjects":["Question-answering systems","Semantic networks (Information theory)","SPARQL (Computer program language)"],"languages":["English","eng"],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://scholar.utc.edu/theses/1033","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Xie, Mengjun","Sakib, Shahnewaz Karim; Liang, Yu","College of Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Schwartz, Major"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-12-01T08:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["University of Tennessee at Chattanooga","Chattanooga (Tenn.)"]},{"key":"dc:relation","label":"Dc Relation","values":["Masters Theses and Doctoral Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["Masters theses","Text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Question-answering systems","Semantic networks (Information theory)","SPARQL (Computer program language)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholar.utc.edu/theses/1033"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Dept. of Computer Science and Engineering","M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science."]},{"key":"dc:description.abstract","label":"Abstract","values":["Knowledge Graph Question Answering (KGQA) pipelines commonly depend on separate entity and relation predictors before querying the graph, which introduces engineering complexity and costly inference passes over large vocabularies. This thesis presents a drop-in replacement for those modules: a fine-tuned large language model (LLM) that translates a natural-language question directly into an executable SPARQL query. We fine-tune instruction-tuned backbones, Llama-3.1-8B-Instruct and Mistral-7B-Instruct, on paired (question, gold SPARQL) examples, which are formatted through chat templates. As a result, the models can perform single-step query generation. The training and inference pipeline includes a lightweight post-processor that corrects tokenizer-induced spacing artifacts in generated SPARQL, improving exact-match robustness without altering query structure. On a held-out test set, the fine-tuned models achieve 97.9% (Llama) and 94.0% (Mistral) exact-match accuracy for natural-language-to-SPARQL generation, demonstrating that an end-to-end translator can meet or exceed the accuracy of typical multi-module KGQA stacks while substantially simplifying the architecture."]},{"key":"dc:title","label":"Title","values":["A question to query LLM as a pipeline replacement in knowledge graph question answering systems"]}]}],"canonical_facts":{"dc:contributor":["Xie, Mengjun","Sakib, Shahnewaz Karim; Liang, Yu","College of Engineering and Computer Science"],"dc:creator":["Schwartz, Major"],"dc:date":["2025-12-01T08:00:00Z"],"dc:description":["Dept. of Computer Science and Engineering","M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science."],"dc:description.abstract":["Knowledge Graph Question Answering (KGQA) pipelines commonly depend on separate entity and relation predictors before querying the graph, which introduces engineering complexity and costly inference passes over large vocabularies. This thesis presents a drop-in replacement for those modules: a fine-tuned large language model (LLM) that translates a natural-language question directly into an executable SPARQL query. We fine-tune instruction-tuned backbones, Llama-3.1-8B-Instruct and Mistral-7B-Instruct, on paired (question, gold SPARQL) examples, which are formatted through chat templates. As a result, the models can perform single-step query generation. The training and inference pipeline includes a lightweight post-processor that corrects tokenizer-induced spacing artifacts in generated SPARQL, improving exact-match robustness without altering query structure. On a held-out test set, the fine-tuned models achieve 97.9% (Llama) and 94.0% (Mistral) exact-match accuracy for natural-language-to-SPARQL generation, demonstrating that an end-to-end translator can meet or exceed the accuracy of typical multi-module KGQA stacks while substantially simplifying the architecture."],"dc:identifier":["https://scholar.utc.edu/theses/1033"],"dc:language":["English","eng"],"dc:publisher":["University of Tennessee at Chattanooga","Chattanooga (Tenn.)"],"dc:relation":["Masters Theses and Doctoral Dissertations"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Question-answering systems","Semantic networks (Information theory)","SPARQL (Computer program language)"],"dc:title":["A question to query LLM as a pipeline replacement in knowledge graph question answering systems"],"dc:type":["Masters theses","Text"]},"updated_at":"2026-07-24T05:47:28Z"}