{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129549"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129549","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Reasoning beyond scale: Structured inference for small language models","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","abstract_has_math":false,"creators":["Aakriti, -"],"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":"2025-04-20","date_published":"2025-04-20","updated_at":"2026-07-22T22:25:05Z","subjects":["Small Language Models","Knowledge Graphs","Question Answering","Claim Verification","Reasoning"],"languages":["en","eng"],"rights":["Copyright 2025 - Aakriti"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129549","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":["Aakriti, -"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-20","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":["Small Language Models","Knowledge Graphs","Question Answering","Claim Verification","Reasoning"]}]},{"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 - Aakriti"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129549"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","The student, - Aakriti, accepted the attached license on 2025-04-20 at 11:03.","The student, - Aakriti, submitted this Thesis for approval on 2025-04-20 at 11:11.","This Thesis was approved for publication on 2025-04-20 at 15:55.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21848 on 2025-10-19 at 19:15:11","Recent progress in large language models (LLMs), such as GPT-4 [1], PaLM [2], and LLaMA [3], has substantially advanced the field of natural language processing (NLP), particularly in tasks requiring reasoning, such as multi-hop question answering (QA) and claim verification [4, 5]. Despite these achievements, such models require significant computational and financial resources, limiting their real-world accessibility [6, 7]. This has motivated a growing interest in small language models (SLMs), typically with fewer than 8 billion parameters, which offer more efficient alternatives. However, SLMs face major challenges when performing complex reasoning under long-context and distractor-rich scenarios, often exhibiting difficulties with factual consistency and multi-step inference [8, 9, 10]. This thesis investigates multi-hop reasoning in small models through the lens of structured knowledge integration, focusing on whether small models can remain grounded in relevant context while avoiding hallucination and distractor interference. Multi-hop reasoning requires the model to chain together intermediate facts and establish logical links across multiple documents or sentences [11]. A key question explored is whether explicit knowledge representations, such as knowledge graphs (KGs), can act as a scaffold to improve logical consistency, contextual grounding, and interpretability in reasoning tasks. The study further examines how SLMs manage cross-document coreference, semantic role tracking, and inference reliability when guided by structured signals. This thesis attempts to identify the linguistic and representational bottlenecks that hinder SLMs from attaining robust reasoning, going beyond surface-level performance. It analyzes the conditions under which models succeed or fail to maintain coherence across reasoning chains, particularly when processing lengthy, noisy input. The thesis also explores how models respond to adversarial distractors and the extent to which structured inputs reduce hallucination rates [12, 13]. Overall, the research contributes to a broader understanding of how reasoning, factuality, and context grounding can be enabled in models – an essential step toward deploying capable and trustworthy NLP systems in real-world environments."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Reasoning beyond scale: Structured inference for small language models"]}]}],"canonical_facts":{"dc:contributor":["Han, Jiawei"],"dc:creator":["Aakriti, -"],"dc:date":["2025-04-20","2025-05"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","The student, - Aakriti, accepted the attached license on 2025-04-20 at 11:03.","The student, - Aakriti, submitted this Thesis for approval on 2025-04-20 at 11:11.","This Thesis was approved for publication on 2025-04-20 at 15:55.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21848 on 2025-10-19 at 19:15:11","Recent progress in large language models (LLMs), such as GPT-4 [1], PaLM [2], and LLaMA [3], has substantially advanced the field of natural language processing (NLP), particularly in tasks requiring reasoning, such as multi-hop question answering (QA) and claim verification [4, 5]. Despite these achievements, such models require significant computational and financial resources, limiting their real-world accessibility [6, 7]. This has motivated a growing interest in small language models (SLMs), typically with fewer than 8 billion parameters, which offer more efficient alternatives. However, SLMs face major challenges when performing complex reasoning under long-context and distractor-rich scenarios, often exhibiting difficulties with factual consistency and multi-step inference [8, 9, 10]. This thesis investigates multi-hop reasoning in small models through the lens of structured knowledge integration, focusing on whether small models can remain grounded in relevant context while avoiding hallucination and distractor interference. Multi-hop reasoning requires the model to chain together intermediate facts and establish logical links across multiple documents or sentences [11]. A key question explored is whether explicit knowledge representations, such as knowledge graphs (KGs), can act as a scaffold to improve logical consistency, contextual grounding, and interpretability in reasoning tasks. The study further examines how SLMs manage cross-document coreference, semantic role tracking, and inference reliability when guided by structured signals. This thesis attempts to identify the linguistic and representational bottlenecks that hinder SLMs from attaining robust reasoning, going beyond surface-level performance. It analyzes the conditions under which models succeed or fail to maintain coherence across reasoning chains, particularly when processing lengthy, noisy input. The thesis also explores how models respond to adversarial distractors and the extent to which structured inputs reduce hallucination rates [12, 13]. Overall, the research contributes to a broader understanding of how reasoning, factuality, and context grounding can be enabled in models – an essential step toward deploying capable and trustworthy NLP systems in real-world environments."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129549"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 - Aakriti"],"dc:subject":["Small Language Models","Knowledge Graphs","Question Answering","Claim Verification","Reasoning"],"dc:title":["Reasoning beyond scale: Structured inference for small 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":"2026-07-22T22:25:05Z"}