{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129259"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129259","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Enhancing large language models: toward more reliable and equitable NLP","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":["Adiga, Rishabh"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Chandrasekaran, Varun"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-28","date_published":"2025-04-28","updated_at":"2026-07-22T22:25:04Z","subjects":["LLM","Few-shot","Attention","Bias","Prompting","Fairness","Metrics","Localization","Mitigation"],"languages":["en","eng"],"rights":["© 2025 Rishabh Adiga"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129259","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chandrasekaran, Varun"]},{"key":"dc:creator","label":"Author","values":["Adiga, Rishabh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-28","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":["LLM","Few-shot","Attention","Bias","Prompting","Fairness","Metrics","Localization","Mitigation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["© 2025 Rishabh Adiga"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129259"]}]},{"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, Rishabh Adiga, accepted the attached license on 2025-04-26 at 09:28.","The student, Rishabh Adiga, submitted this Thesis for approval on 2025-04-26 at 09:34.","This Thesis was approved for publication on 2025-04-28 at 18:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22007 on 2025-10-19 at 18:11:05","Recent advances in large language models (LLMs) have enabled them to achieve striking fewshot performance on complex tasks, yet they can remain sensitive to prompt configurations and prone to subtle biases. This thesis addresses two central problems: (1) selecting informative few-shot examples and (2) localizing and mitigating bias in ambiguous comparative prompts. First, we propose a complexity-based approach for selecting examples in few-shot sequence tagging tasks, aiming to align test examples with training examples based on syntactic and semantic metrics. By focusing on features like sentence similarity, length matching, and label diversity, we achieve more consistent and robust outcomes without fine-tuning or adding parameters. Second, we develop a method to localize and mitigate bias in LLMs by examining the attention layers that favor certain entities over others. We then scale attention in those identified layers to reduce skewed preferences, preserving overall model fluency while mitigating biases. Extensive evaluations confirm that this targeted attention manipulation provides a lightweight way to address fairness concerns without sacrificing downstream accuracy."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Enhancing large language models: toward more reliable and equitable NLP"]}]}],"canonical_facts":{"dc:contributor":["Chandrasekaran, Varun"],"dc:creator":["Adiga, Rishabh"],"dc:date":["2025-04-28","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, Rishabh Adiga, accepted the attached license on 2025-04-26 at 09:28.","The student, Rishabh Adiga, submitted this Thesis for approval on 2025-04-26 at 09:34.","This Thesis was approved for publication on 2025-04-28 at 18:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22007 on 2025-10-19 at 18:11:05","Recent advances in large language models (LLMs) have enabled them to achieve striking fewshot performance on complex tasks, yet they can remain sensitive to prompt configurations and prone to subtle biases. This thesis addresses two central problems: (1) selecting informative few-shot examples and (2) localizing and mitigating bias in ambiguous comparative prompts. First, we propose a complexity-based approach for selecting examples in few-shot sequence tagging tasks, aiming to align test examples with training examples based on syntactic and semantic metrics. By focusing on features like sentence similarity, length matching, and label diversity, we achieve more consistent and robust outcomes without fine-tuning or adding parameters. Second, we develop a method to localize and mitigate bias in LLMs by examining the attention layers that favor certain entities over others. We then scale attention in those identified layers to reduce skewed preferences, preserving overall model fluency while mitigating biases. Extensive evaluations confirm that this targeted attention manipulation provides a lightweight way to address fairness concerns without sacrificing downstream accuracy."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129259"],"dc:language":["en","eng"],"dc:rights":["© 2025 Rishabh Adiga"],"dc:subject":["LLM","Few-shot","Attention","Bias","Prompting","Fairness","Metrics","Localization","Mitigation"],"dc:title":["Enhancing large language models: toward more reliable and equitable NLP"],"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"}