{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129221"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129221","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"PropRAG: Guiding retrieval with beam search over proposition paths","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":["Wang, William"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Han, Jiawei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-22","date_published":"2025-04-22","updated_at":"2026-07-22T22:25:04Z","subjects":["Retrieval Augmented Generation","RAG","Multi-Hop RAG","Question Answering","Proposition","Beam Search","Non-Parametric Continual Learning"],"languages":["en","eng"],"rights":["Copyright 2025 William Wang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129221","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Han, Jiawei"]},{"key":"dc:creator","label":"Author","values":["Wang, William"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-22","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":["Retrieval Augmented Generation","RAG","Multi-Hop RAG","Question Answering","Proposition","Beam Search","Non-Parametric Continual Learning"]}]},{"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 William Wang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129221"]}]},{"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, William Wang, accepted the attached license on 2025-04-18 at 20:59.","The student, William Wang, submitted this Thesis for approval on 2025-04-18 at 21:04.","This Thesis was approved for publication on 2025-04-22 at 11:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21844 on 2025-10-19 at 18:09:33","Retrieval Augmented Generation (RAG) has become the standard non-parametric approach for equipping Large Language Models (LLMs) with up-to-date knowledge and mitigating catastrophic forgetting common in continual learning. However, standard RAG, relying on independent passage retrieval, fails to capture the interconnected nature of human memory crucial for complex reasoning (associativity) and contextual understanding (sense-making). While structured RAG methods like HippoRAG 2 [1] utilize knowledge graphs (KGs) built from triples to improve associativity, the inherent context loss in triples limits their fidelity. We introduce PropRAG, a framework advancing RAG towards more human-like memory capabilities. PropRAG leverages contextually rich propositions as knowledge units and introduces a novel beam search algorithm over proposition paths, inspired by sequence generation, to explicitly discover and score multi-step reasoning chains. This path-centric approach significantly enhances multi-hop reasoning. PropRAG achieves state-of-the-art zero-shot Recall@5 results on challenging benchmarks like PopQA (55.3%), 2Wiki (93.7%), HotpotQA (97.0%), and MuSiQue (77.3%), alongside top F1 scores, including 52.4% on MuSiQue using Llama-3.3-Instruct. By improving the retrieval of interconnected evidence through richer representation and explicit path finding, PropRAG advances non-parametric continual learning for LLMs."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["PropRAG: Guiding retrieval with beam search over proposition paths"]}]}],"canonical_facts":{"dc:contributor":["Han, Jiawei"],"dc:creator":["Wang, William"],"dc:date":["2025-04-22","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, William Wang, accepted the attached license on 2025-04-18 at 20:59.","The student, William Wang, submitted this Thesis for approval on 2025-04-18 at 21:04.","This Thesis was approved for publication on 2025-04-22 at 11:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21844 on 2025-10-19 at 18:09:33","Retrieval Augmented Generation (RAG) has become the standard non-parametric approach for equipping Large Language Models (LLMs) with up-to-date knowledge and mitigating catastrophic forgetting common in continual learning. However, standard RAG, relying on independent passage retrieval, fails to capture the interconnected nature of human memory crucial for complex reasoning (associativity) and contextual understanding (sense-making). While structured RAG methods like HippoRAG 2 [1] utilize knowledge graphs (KGs) built from triples to improve associativity, the inherent context loss in triples limits their fidelity. We introduce PropRAG, a framework advancing RAG towards more human-like memory capabilities. PropRAG leverages contextually rich propositions as knowledge units and introduces a novel beam search algorithm over proposition paths, inspired by sequence generation, to explicitly discover and score multi-step reasoning chains. This path-centric approach significantly enhances multi-hop reasoning. PropRAG achieves state-of-the-art zero-shot Recall@5 results on challenging benchmarks like PopQA (55.3%), 2Wiki (93.7%), HotpotQA (97.0%), and MuSiQue (77.3%), alongside top F1 scores, including 52.4% on MuSiQue using Llama-3.3-Instruct. By improving the retrieval of interconnected evidence through richer representation and explicit path finding, PropRAG advances non-parametric continual learning for LLMs."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129221"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 William Wang"],"dc:subject":["Retrieval Augmented Generation","RAG","Multi-Hop RAG","Question Answering","Proposition","Beam Search","Non-Parametric Continual Learning"],"dc:title":["PropRAG: Guiding retrieval with beam search over proposition paths"],"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"}