{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/162742"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/162742","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Injection of Domain-Specific Knowledge for Enterprise Text-to-SQL","abstract":"This work examines the current state of using large language models (LLMs) to solve Text-to-SQL tasks on databases in an enterprise setting. Benchmarks on publicly available datasets do not fully capture the difficulty and complexity of this task in a real-world, enterprise setting. This study examines the critical steps needed to work with enterprise data as well as using knowledge-injection to enhance the performance of LLMs on Text-to-SQL tasks. We begin by evaluating the baseline performance of LLMs on enterprise databases, revealing that a predominant source of failure stems from a lack of domain-specific knowledge. To improve performance, we explore knowledge-injection: the process of incorporating internal and external knowledge. Internal knowledge consists of database-specific information such as join logic, while external knowledge refers to institutional acronyms or group names. We present a hybrid retrieval pipeline that combines embedding and text based searching with LLM-guided ranking to supply models with relevant external knowledge during Text-to-SQL generation. We evaluate the impact of the knowledge-injection by testing the performance of LLMs on the table retrieval task after being augmented with appropriate external knowledge. We demonstrate that knowledge-injection significantly improves accuracy on table retrieval using BEAVER: an enterprise-level Text-to-SQL benchmark. Our findings highlight the importance of domain-specific knowledge-injection and retrieval augmentation in bringing LLMs closer to deployment in enterprise-grade database systems, as well as common failure modes that occur when executing enterprise Text-to-SQL.","abstract_html":"This work examines the current state of using large language models (LLMs) to solve Text-to-SQL tasks on databases in an enterprise setting. Benchmarks on publicly available datasets do not fully capture the difficulty and complexity of this task in a real-world, enterprise setting. This study examines the critical steps needed to work with enterprise data as well as using knowledge-injection to enhance the performance of LLMs on Text-to-SQL tasks. We begin by evaluating the baseline performance of LLMs on enterprise databases, revealing that a predominant source of failure stems from a lack of domain-specific knowledge. To improve performance, we explore knowledge-injection: the process of incorporating internal and external knowledge. Internal knowledge consists of database-specific information such as join logic, while external knowledge refers to institutional acronyms or group names. We present a hybrid retrieval pipeline that combines embedding and text based searching with LLM-guided ranking to supply models with relevant external knowledge during Text-to-SQL generation. We evaluate the impact of the knowledge-injection by testing the performance of LLMs on the table retrieval task after being augmented with appropriate external knowledge. We demonstrate that knowledge-injection significantly improves accuracy on table retrieval using BEAVER: an enterprise-level Text-to-SQL benchmark. Our findings highlight the importance of domain-specific knowledge-injection and retrieval augmentation in bringing LLMs closer to deployment in enterprise-grade database systems, as well as common failure modes that occur when executing enterprise Text-to-SQL.","abstract_has_math":false,"creators":["Choi, Justin J."],"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":["Stonebraker, Michael R."],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-22T22:21:49Z","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/1721.1/162742","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Stonebraker, Michael R."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Choi, Justin J."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-18T14:30:08Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-18T14:30:08Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"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/1721.1/162742"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This work examines the current state of using large language models (LLMs) to solve Text-to-SQL tasks on databases in an enterprise setting. Benchmarks on publicly available datasets do not fully capture the difficulty and complexity of this task in a real-world, enterprise setting. This study examines the critical steps needed to work with enterprise data as well as using knowledge-injection to enhance the performance of LLMs on Text-to-SQL tasks. We begin by evaluating the baseline performance of LLMs on enterprise databases, revealing that a predominant source of failure stems from a lack of domain-specific knowledge. To improve performance, we explore knowledge-injection: the process of incorporating internal and external knowledge. Internal knowledge consists of database-specific information such as join logic, while external knowledge refers to institutional acronyms or group names. We present a hybrid retrieval pipeline that combines embedding and text based searching with LLM-guided ranking to supply models with relevant external knowledge during Text-to-SQL generation. We evaluate the impact of the knowledge-injection by testing the performance of LLMs on the table retrieval task after being augmented with appropriate external knowledge. We demonstrate that knowledge-injection significantly improves accuracy on table retrieval using BEAVER: an enterprise-level Text-to-SQL benchmark. Our findings highlight the importance of domain-specific knowledge-injection and retrieval augmentation in bringing LLMs closer to deployment in enterprise-grade database systems, as well as common failure modes that occur when executing enterprise Text-to-SQL."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Injection of Domain-Specific Knowledge for Enterprise Text-to-SQL"]}]}],"canonical_facts":{"dc:contributor.advisor":["Stonebraker, Michael R."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Choi, Justin J."],"dc:date.accessioned":["2025-09-18T14:30:08Z"],"dc:date.available":["2025-09-18T14:30:08Z"],"dc:date.issued":["2025-05"],"dc:description.abstract":["This work examines the current state of using large language models (LLMs) to solve Text-to-SQL tasks on databases in an enterprise setting. Benchmarks on publicly available datasets do not fully capture the difficulty and complexity of this task in a real-world, enterprise setting. This study examines the critical steps needed to work with enterprise data as well as using knowledge-injection to enhance the performance of LLMs on Text-to-SQL tasks. We begin by evaluating the baseline performance of LLMs on enterprise databases, revealing that a predominant source of failure stems from a lack of domain-specific knowledge. To improve performance, we explore knowledge-injection: the process of incorporating internal and external knowledge. Internal knowledge consists of database-specific information such as join logic, while external knowledge refers to institutional acronyms or group names. We present a hybrid retrieval pipeline that combines embedding and text based searching with LLM-guided ranking to supply models with relevant external knowledge during Text-to-SQL generation. We evaluate the impact of the knowledge-injection by testing the performance of LLMs on the table retrieval task after being augmented with appropriate external knowledge. We demonstrate that knowledge-injection significantly improves accuracy on table retrieval using BEAVER: an enterprise-level Text-to-SQL benchmark. Our findings highlight the importance of domain-specific knowledge-injection and retrieval augmentation in bringing LLMs closer to deployment in enterprise-grade database systems, as well as common failure modes that occur when executing enterprise Text-to-SQL."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/162742"],"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":["Injection of Domain-Specific Knowledge for Enterprise Text-to-SQL"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:49Z"}