{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/120265"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/120265","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Enhancing diversity in generative commonsense reasoning for explaining relationships between concepts","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","abstract_has_math":false,"creators":["Liu, Chenzhengyi"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Chang, Kevin Chen-Chuan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-05","date_published":"2023-05","updated_at":"2026-07-22T22:24:57Z","subjects":["Natural Language Processing","Commonsense Reasoning","Diverse Text Generation","Large Language Models","Mixture Of Experts","Cold Decoding"],"languages":["en","eng"],"rights":["Copyright 2023 Chenzhengyi Liu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/120265","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chang, Kevin Chen-Chuan"]},{"key":"dc:creator","label":"Author","values":["Liu, Chenzhengyi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-05","2023-04-16"]},{"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 at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Natural Language Processing","Commonsense Reasoning","Diverse Text Generation","Large Language Models","Mixture Of Experts","Cold Decoding"]}]},{"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 2023 Chenzhengyi Liu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/120265"]}]},{"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 2023-09-01 without embargo terms","The student, Chenzhengyi Liu, accepted the attached license on 2023-04-14 at 10:11.","The student, Chenzhengyi Liu, submitted this Thesis for approval on 2023-04-14 at 10:20.","This Thesis was approved for publication on 2023-04-16 at 12:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #18981 on 2023-09-01 at 17:08:34","The ability to reason based on common sense and knowledge of how things work is crucial for machines to navigate the world. However, large language models (LLMs) often lack explicit representations of relationships between concepts and events, making it challenging to interpret their reasoning processes. To overcome these challenges, in this paper, we propose DimonGen task, which aims to generate diverse sentences describing concept relationships in various everyday scenarios. To support this, we also create a new benchmark dataset for this task by extracting the existing ConceptNet and CommonGen dataset. To address the DimonGen task, we propose two complementary methods: MoREE, a two-stage method that utilizes external knowledge to generate diverse relationship sentences, and DC Decoding, a decoding framework that uses a global energy function to diversify the set of generations. Both methods are evaluated on the benchmark dataset and show significant improvements in the quality and diversity of generated sentences. The results suggest that these methods can generate diverse sentences that reflect relationships between concepts from multiple and varied perspectives. Our code and data for the DimmonGen task are available at https://github.com/liuchenzhengyi/DimonGen."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Enhancing diversity in generative commonsense reasoning for explaining relationships between concepts"]}]}],"canonical_facts":{"dc:contributor":["Chang, Kevin Chen-Chuan"],"dc:creator":["Liu, Chenzhengyi"],"dc:date":["2023-05","2023-04-16"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","The student, Chenzhengyi Liu, accepted the attached license on 2023-04-14 at 10:11.","The student, Chenzhengyi Liu, submitted this Thesis for approval on 2023-04-14 at 10:20.","This Thesis was approved for publication on 2023-04-16 at 12:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #18981 on 2023-09-01 at 17:08:34","The ability to reason based on common sense and knowledge of how things work is crucial for machines to navigate the world. However, large language models (LLMs) often lack explicit representations of relationships between concepts and events, making it challenging to interpret their reasoning processes. To overcome these challenges, in this paper, we propose DimonGen task, which aims to generate diverse sentences describing concept relationships in various everyday scenarios. To support this, we also create a new benchmark dataset for this task by extracting the existing ConceptNet and CommonGen dataset. To address the DimonGen task, we propose two complementary methods: MoREE, a two-stage method that utilizes external knowledge to generate diverse relationship sentences, and DC Decoding, a decoding framework that uses a global energy function to diversify the set of generations. Both methods are evaluated on the benchmark dataset and show significant improvements in the quality and diversity of generated sentences. The results suggest that these methods can generate diverse sentences that reflect relationships between concepts from multiple and varied perspectives. Our code and data for the DimmonGen task are available at https://github.com/liuchenzhengyi/DimonGen."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/120265"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Chenzhengyi Liu"],"dc:subject":["Natural Language Processing","Commonsense Reasoning","Diverse Text Generation","Large Language Models","Mixture Of Experts","Cold Decoding"],"dc:title":["Enhancing diversity in generative commonsense reasoning for explaining relationships between concepts"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:57Z"}