{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129450"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129450","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"An ontology-guided, language model-assisted approach for theme-specific information extraction","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_has_math":false,"creators":["Xiao, Jinfeng"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Han, Jiawei","Zhai, ChengXiang","Ji, Heng","Elkaref, Mohab"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-25","date_published":"2025-04-25","updated_at":"2026-07-22T22:25:05Z","subjects":["Large language models","Information extraction","Information retrieval","Ontology","Taxonomy"],"languages":["en","eng"],"rights":["Copyright 2025 Jinfeng Xiao"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129450","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Han, Jiawei","Zhai, ChengXiang","Ji, Heng","Elkaref, Mohab"]},{"key":"dc:creator","label":"Author","values":["Xiao, Jinfeng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-25","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Large language models","Information extraction","Information retrieval","Ontology","Taxonomy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Jinfeng Xiao"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129450"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Jinfeng Xiao, accepted the attached license on 2025-04-25 at 13:12.","The student, Jinfeng Xiao, submitted this Dissertation for approval on 2025-04-25 at 13:37.","This Dissertation was approved for publication on 2025-04-25 at 16:40.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21985 on 2025-10-19 at 18:19:17","In an era of information explosion, text data are generated every second so fast that digesting raw texts becomes increasingly time-consuming. The research field of text mining aims at automatically extracting structured knowledge from massive unstructured text data. An essential step in the process of converting text to knowledge is information extraction (IE), which aims at extracting information about entities and relations from text. In recent years, the development of large language models (LLMs) has shed light on new possibilities of performing better IE under label-sparse settings that are hard, if not impossible, for traditional methods due to the lack of human supervision that is necessary for model training. On the other hand, LLM-assisted domain-specific IE applications often face long-tail challenges, which refer to suboptimal performance due to the fact that many important signals (e.g., entities and relations) in the target domain are sparse in the pre-training corpora and are thus not handled well by pre-trained LLMs. Such long-tail problems become more severe when we move one step further from domains into highly specialized themes. My dissertation research explores the utilization of theme-specific entity type ontologies to improve the long-tail robustness of LLMs for IE tasks. I utilize such ontologies to 1) retrieve theme-relevant documents from large corpora based on the distribution of query entities and relations on the ontology, 2) find entities from large corpora that have fine-grained entity types relevant to the query entities, 3) retrieve relevant external, non-parametric knowledge in a structured manner to augment LLM queries, and 4) organize the internal, parametric knowledge of LLMs into relation structures for robust open relation extraction. While the 1st and 3rd components focus more on information retrieval (IR), all the components together form an end-to-end framework for corpus-level theme-specific IE. Extensive experiments demonstrate that my solutions achieve state-of-the-art performance with remarkable long-tail robustness. One more notable advantage of my approach is that it works purely at the LLM inference stage. No extra pre-training or post-training is required. This means my approach works without additional annotation efforts or heavy resource consumption. All my methods are easy to deploy on a single graphics processing unit (GPU) with any recent LLMs, and thus, my solutions are highly accessible to ordinary people. In addition, my design essentially separates data from models, which ensures there is technically zero risk of leaking private user data. Thus, my approach is highly suitable for sensitive domain applications such as medical care and legal advising."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["An ontology-guided, language model-assisted approach for theme-specific information extraction"]}]}],"canonical_facts":{"dc:contributor":["Han, Jiawei","Zhai, ChengXiang","Ji, Heng","Elkaref, Mohab"],"dc:creator":["Xiao, Jinfeng"],"dc:date":["2025-04-25","2025-05"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Jinfeng Xiao, accepted the attached license on 2025-04-25 at 13:12.","The student, Jinfeng Xiao, submitted this Dissertation for approval on 2025-04-25 at 13:37.","This Dissertation was approved for publication on 2025-04-25 at 16:40.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21985 on 2025-10-19 at 18:19:17","In an era of information explosion, text data are generated every second so fast that digesting raw texts becomes increasingly time-consuming. The research field of text mining aims at automatically extracting structured knowledge from massive unstructured text data. An essential step in the process of converting text to knowledge is information extraction (IE), which aims at extracting information about entities and relations from text. In recent years, the development of large language models (LLMs) has shed light on new possibilities of performing better IE under label-sparse settings that are hard, if not impossible, for traditional methods due to the lack of human supervision that is necessary for model training. On the other hand, LLM-assisted domain-specific IE applications often face long-tail challenges, which refer to suboptimal performance due to the fact that many important signals (e.g., entities and relations) in the target domain are sparse in the pre-training corpora and are thus not handled well by pre-trained LLMs. Such long-tail problems become more severe when we move one step further from domains into highly specialized themes. My dissertation research explores the utilization of theme-specific entity type ontologies to improve the long-tail robustness of LLMs for IE tasks. I utilize such ontologies to 1) retrieve theme-relevant documents from large corpora based on the distribution of query entities and relations on the ontology, 2) find entities from large corpora that have fine-grained entity types relevant to the query entities, 3) retrieve relevant external, non-parametric knowledge in a structured manner to augment LLM queries, and 4) organize the internal, parametric knowledge of LLMs into relation structures for robust open relation extraction. While the 1st and 3rd components focus more on information retrieval (IR), all the components together form an end-to-end framework for corpus-level theme-specific IE. Extensive experiments demonstrate that my solutions achieve state-of-the-art performance with remarkable long-tail robustness. One more notable advantage of my approach is that it works purely at the LLM inference stage. No extra pre-training or post-training is required. This means my approach works without additional annotation efforts or heavy resource consumption. All my methods are easy to deploy on a single graphics processing unit (GPU) with any recent LLMs, and thus, my solutions are highly accessible to ordinary people. In addition, my design essentially separates data from models, which ensures there is technically zero risk of leaking private user data. Thus, my approach is highly suitable for sensitive domain applications such as medical care and legal advising."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129450"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Jinfeng Xiao"],"dc:subject":["Large language models","Information extraction","Information retrieval","Ontology","Taxonomy"],"dc:title":["An ontology-guided, language model-assisted approach for theme-specific information extraction"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:05Z"}