{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129215"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129215","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Event-based knowledge editing for deterministic knowledge propagation in large language models","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":["Liu, Jiateng"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Ji, Heng"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-17","date_published":"2025-04-17","updated_at":"2026-07-22T22:25:04Z","subjects":["Knowledge Editing","Language Models"],"languages":["en","eng"],"rights":["Copyright 2025 Jiateng Liu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129215","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ji, Heng"]},{"key":"dc:creator","label":"Author","values":["Liu, Jiateng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-17","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":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"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":["Knowledge Editing","Language Models"]}]},{"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 Jiateng Liu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129215"]}]},{"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, Jiateng Liu, accepted the attached license on 2025-04-17 at 10:21.","The student, Jiateng Liu, submitted this Thesis for approval on 2025-04-17 at 10:21.","This Thesis was approved for publication on 2025-04-17 at 13:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21819 on 2025-10-19 at 18:09:31","The dynamic nature of real-world information necessitates knowledge editing (KE) in large language models (LLMs). This edited knowledge should propagate and facilitate the deduction of new information based on existing model knowledge. We define the existing related knowledge in a LLM serving as the origination of knowledge propagation as ``deduction anchors''. However, most of current KE approaches only operate on (subject, relation, object) triples. Both theoretically and empirically, we observe that this simplified setting often leads to uncertainty when determining the deduction anchors, causing low confidence in their responses. To mitigate this issue, we propose a novel task of event-based knowledge editing that pairs facts with event descriptions. This task manifests both as a closer simulation of real-world editing scenarios and a more logically sound setting, implicitly defining the deduction anchor and enabling LLMs to propagate knowledge confidently. We curate a new benchmark dataset evedit derived from the CounterFact dataset and validate its superiority in improving model confidence. Moreover, as we observe that the event-based setting is notably challenging for existing approaches, we propose a novel approach Self-Edit that showcases stronger performance, achieving 55.6\\% consistency improvement while maintaining the naturalness of generation."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Event-based knowledge editing for deterministic knowledge propagation in large language models"]}]}],"canonical_facts":{"dc:contributor":["Ji, Heng"],"dc:creator":["Liu, Jiateng"],"dc:date":["2025-04-17","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, Jiateng Liu, accepted the attached license on 2025-04-17 at 10:21.","The student, Jiateng Liu, submitted this Thesis for approval on 2025-04-17 at 10:21.","This Thesis was approved for publication on 2025-04-17 at 13:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21819 on 2025-10-19 at 18:09:31","The dynamic nature of real-world information necessitates knowledge editing (KE) in large language models (LLMs). This edited knowledge should propagate and facilitate the deduction of new information based on existing model knowledge. We define the existing related knowledge in a LLM serving as the origination of knowledge propagation as ``deduction anchors''. However, most of current KE approaches only operate on (subject, relation, object) triples. Both theoretically and empirically, we observe that this simplified setting often leads to uncertainty when determining the deduction anchors, causing low confidence in their responses. To mitigate this issue, we propose a novel task of event-based knowledge editing that pairs facts with event descriptions. This task manifests both as a closer simulation of real-world editing scenarios and a more logically sound setting, implicitly defining the deduction anchor and enabling LLMs to propagate knowledge confidently. We curate a new benchmark dataset evedit derived from the CounterFact dataset and validate its superiority in improving model confidence. Moreover, as we observe that the event-based setting is notably challenging for existing approaches, we propose a novel approach Self-Edit that showcases stronger performance, achieving 55.6\\% consistency improvement while maintaining the naturalness of generation."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129215"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Jiateng Liu"],"dc:subject":["Knowledge Editing","Language Models"],"dc:title":["Event-based knowledge editing for deterministic knowledge propagation in large language models"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:04Z"}