{"id":{"repo_id":"sdstate","oai_identifier":"oai:openprairie.sdstate.edu:etd2-2874"},"canonical_url":"https://search.ndltd.org/etd/sdstate/oai:openprairie.sdstate.edu:etd2-2874","repository":{"repo_id":"sdstate","name":"South Dakota State University","base_url":"https://openprairie.sdstate.edu/do/oai/"},"display":{"title":"Semantic Think-on-Graph (SemToG) : Enhancing GraphRAG through Semantic Community Detection","abstract":"Graph-based Retrieval-Augmented Generation (GraphRAG) enhances large language models (LLMs) by grounding their reasoning in structured knowledge graphs, making them more reliable for multi-hop reasoning and factual QA. A central mechanism in Think-on-Graph systems such as ToG[14] and FastToG[7] is community detection, which groups locally related nodes into compact subgraphs so that LLMs can reason over focused, information-rich neighborhoods instead of traversing the entire graph. However, these methods rely purely on structural connectivity, often scattering semantically related entities across different communities and weakening the evidence provided to the LLM. We propose Semantic Think-on-Graph (SemToG), a semantic-aware extension of FastToG[7] that integrates node and relation embeddings directly into community detection through relation-query similarity, entity relevance, hop-aware propagation, and answer-type intent. By combining structural connectivity with semantic alignment, SemToG constructs query-relevant communities that deliver more coherent evidence for LLM reasoning. We evaluate SemToG on six benchmark datasets : CWQ [15], WebQSP[19], QALD[12],ZSRE[13], TREx [3], and Creak [10]-measuring answer accuracy and reasoning steps. SemToG achieves consistent gains of 2-5% accuracy over FastToG[7] while requiring fewer community-expansion steps, demonstrating improved retrieval precision, semantic consistency, and computational efficiency. These results highlight the significance of incorporating semantic-aware community formation into GraphRAG pipelines and point toward more robust and contextually aligned knowledge-grounded LLM systems.","abstract_html":"Graph-based Retrieval-Augmented Generation (GraphRAG) enhances large language models (LLMs) by grounding their reasoning in structured knowledge graphs, making them more reliable for multi-hop reasoning and factual QA. A central mechanism in Think-on-Graph systems such as ToG[14] and FastToG[7] is community detection, which groups locally related nodes into compact subgraphs so that LLMs can reason over focused, information-rich neighborhoods instead of traversing the entire graph. However, these methods rely purely on structural connectivity, often scattering semantically related entities across different communities and weakening the evidence provided to the LLM. We propose Semantic Think-on-Graph (SemToG), a semantic-aware extension of FastToG[7] that integrates node and relation embeddings directly into community detection through relation-query similarity, entity relevance, hop-aware propagation, and answer-type intent. By combining structural connectivity with semantic alignment, SemToG constructs query-relevant communities that deliver more coherent evidence for LLM reasoning. We evaluate SemToG on six benchmark datasets : CWQ [15], WebQSP[19], QALD[12],ZSRE[13], TREx [3], and Creak [10]-measuring answer accuracy and reasoning steps. SemToG achieves consistent gains of 2-5% accuracy over FastToG[7] while requiring fewer community-expansion steps, demonstrating improved retrieval precision, semantic consistency, and computational efficiency. These results highlight the significance of incorporating semantic-aware community formation into GraphRAG pipelines and point toward more robust and contextually aligned knowledge-grounded LLM systems.","abstract_has_math":false,"creators":["Mishra, Sugam"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis - Open Access","degree_discipline":"Electrical Engineering and Computer Science","degree_department":null,"school":null,"contributors":["Chulwoo Pack"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:05:56Z","subjects":["Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://openprairie.sdstate.edu/etd2/1863","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://openprairie.sdstate.edu/etd2/1863","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://openprairie.sdstate.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopenprairie.sdstate.edu%3Aetd2-2874","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chulwoo Pack"]},{"key":"dc:creator","label":"Author","values":["Mishra, Sugam"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-23T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering and Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical and Computer Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"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://openprairie.sdstate.edu/etd2/1863"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Graph-based Retrieval-Augmented Generation (GraphRAG) enhances large language models (LLMs) by grounding their reasoning in structured knowledge graphs, making them more reliable for multi-hop reasoning and factual QA. A central mechanism in Think-on-Graph systems such as ToG[14] and FastToG[7] is community detection, which groups locally related nodes into compact subgraphs so that LLMs can reason over focused, information-rich neighborhoods instead of traversing the entire graph. However, these methods rely purely on structural connectivity, often scattering semantically related entities across different communities and weakening the evidence provided to the LLM. We propose Semantic Think-on-Graph (SemToG), a semantic-aware extension of FastToG[7] that integrates node and relation embeddings directly into community detection through relation-query similarity, entity relevance, hop-aware propagation, and answer-type intent. By combining structural connectivity with semantic alignment, SemToG constructs query-relevant communities that deliver more coherent evidence for LLM reasoning. We evaluate SemToG on six benchmark datasets : CWQ [15], WebQSP[19], QALD[12],ZSRE[13], TREx [3], and Creak [10]-measuring answer accuracy and reasoning steps. SemToG achieves consistent gains of 2-5% accuracy over FastToG[7] while requiring fewer community-expansion steps, demonstrating improved retrieval precision, semantic consistency, and computational efficiency. These results highlight the significance of incorporating semantic-aware community formation into GraphRAG pipelines and point toward more robust and contextually aligned knowledge-grounded LLM systems."]},{"key":"dc:title","label":"Title","values":["Semantic Think-on-Graph (SemToG) : Enhancing GraphRAG through Semantic Community Detection"]}]}],"canonical_facts":{"dc:contributor":["Chulwoo Pack"],"dc:creator":["Mishra, Sugam"],"dc:date.available":["2026-01-23T08:00:00Z"],"dc:date.created":["2025-01-01T08:00:00Z"],"dc:description.abstract":["Graph-based Retrieval-Augmented Generation (GraphRAG) enhances large language models (LLMs) by grounding their reasoning in structured knowledge graphs, making them more reliable for multi-hop reasoning and factual QA. A central mechanism in Think-on-Graph systems such as ToG[14] and FastToG[7] is community detection, which groups locally related nodes into compact subgraphs so that LLMs can reason over focused, information-rich neighborhoods instead of traversing the entire graph. However, these methods rely purely on structural connectivity, often scattering semantically related entities across different communities and weakening the evidence provided to the LLM. We propose Semantic Think-on-Graph (SemToG), a semantic-aware extension of FastToG[7] that integrates node and relation embeddings directly into community detection through relation-query similarity, entity relevance, hop-aware propagation, and answer-type intent. By combining structural connectivity with semantic alignment, SemToG constructs query-relevant communities that deliver more coherent evidence for LLM reasoning. We evaluate SemToG on six benchmark datasets : CWQ [15], WebQSP[19], QALD[12],ZSRE[13], TREx [3], and Creak [10]-measuring answer accuracy and reasoning steps. SemToG achieves consistent gains of 2-5% accuracy over FastToG[7] while requiring fewer community-expansion steps, demonstrating improved retrieval precision, semantic consistency, and computational efficiency. These results highlight the significance of incorporating semantic-aware community formation into GraphRAG pipelines and point toward more robust and contextually aligned knowledge-grounded LLM systems."],"dc:identifier":["https://openprairie.sdstate.edu/etd2/1863"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Electrical and Computer Engineering"],"dc:title":["Semantic Think-on-Graph (SemToG) : Enhancing GraphRAG through Semantic Community Detection"],"thesis:degree_discipline":["Electrical Engineering and Computer Science"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T09:05:56Z"}