{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129520"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129520","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Social stereotypes in text-to-image generation: Examining user perceptions and debiasing strategies","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":["Barve, Saharsh Sandeep"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Saha, Koustuv"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-10","date_published":"2025-04-10","updated_at":"2026-07-22T22:25:05Z","subjects":["Generative AI","Social Computing","Text-to-Image Generation","Social Stereotypes","User Perception","Large Language Models","Human-Computer Interaction"],"languages":["en","eng"],"rights":["Copyright 2025 Saharsh Barve"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129520","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Saha, Koustuv"]},{"key":"dc:creator","label":"Author","values":["Barve, Saharsh Sandeep"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-10","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":["Generative AI","Social Computing","Text-to-Image Generation","Social Stereotypes","User Perception","Large Language Models","Human-Computer Interaction"]}]},{"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 Saharsh Barve"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129520"]}]},{"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, Saharsh Barve, accepted the attached license on 2025-04-10 at 11:40.","The student, Saharsh Barve, submitted this Thesis for approval on 2025-04-10 at 11:42.","This Thesis was approved for publication on 2025-04-10 at 11:48.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21737 on 2025-10-19 at 19:14:37","The rise of generative AI has fueled a shift from traditional search-based image retrieval to text-based image synthesis. While this advancement enables more creative and dynamic image generation, it also raises significant ethical concerns. The growing use of AI-generated images risks reinforcing or even amplifying societal stereotypes related to gender, race, and ethnicity, ultimately contributing to social divisions and distorting cultural representation in our digital world. As these technologies scale, robust frameworks to assess and mitigate social biases remain lacking. Our research addresses this gap by proposing an evaluation mechanism that leverages LLMs as judges while keeping humans in the loop. We evaluate this method across three prompt categories—Geocultural, Occupational, and Adjective—and three T2I models (DALL·E 3, Midjourney v6.1, and Stability AI Core). Additionally, we present a user study to understand how users perceive generated images and the social stereotypes embedded within them, ensuring our approach aligns with real-world expectations. Our findings reveal a key tension: while explicit prompt refinement can reduce stereotypical cues in images, it can also reduce contextual alignment to the original prompt. Conversely, our user study reveals how people often relate to stereotypical cues as more contextually relevant and recognizable. Our work seeks to ensure that text-based image synthesis preserves global diversity, fosters social inclusivity, and accurately represents real-world society."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Social stereotypes in text-to-image generation: Examining user perceptions and debiasing strategies"]}]}],"canonical_facts":{"dc:contributor":["Saha, Koustuv"],"dc:creator":["Barve, Saharsh Sandeep"],"dc:date":["2025-04-10","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, Saharsh Barve, accepted the attached license on 2025-04-10 at 11:40.","The student, Saharsh Barve, submitted this Thesis for approval on 2025-04-10 at 11:42.","This Thesis was approved for publication on 2025-04-10 at 11:48.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21737 on 2025-10-19 at 19:14:37","The rise of generative AI has fueled a shift from traditional search-based image retrieval to text-based image synthesis. While this advancement enables more creative and dynamic image generation, it also raises significant ethical concerns. The growing use of AI-generated images risks reinforcing or even amplifying societal stereotypes related to gender, race, and ethnicity, ultimately contributing to social divisions and distorting cultural representation in our digital world. As these technologies scale, robust frameworks to assess and mitigate social biases remain lacking. Our research addresses this gap by proposing an evaluation mechanism that leverages LLMs as judges while keeping humans in the loop. We evaluate this method across three prompt categories—Geocultural, Occupational, and Adjective—and three T2I models (DALL·E 3, Midjourney v6.1, and Stability AI Core). Additionally, we present a user study to understand how users perceive generated images and the social stereotypes embedded within them, ensuring our approach aligns with real-world expectations. Our findings reveal a key tension: while explicit prompt refinement can reduce stereotypical cues in images, it can also reduce contextual alignment to the original prompt. Conversely, our user study reveals how people often relate to stereotypical cues as more contextually relevant and recognizable. Our work seeks to ensure that text-based image synthesis preserves global diversity, fosters social inclusivity, and accurately represents real-world society."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129520"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Saharsh Barve"],"dc:subject":["Generative AI","Social Computing","Text-to-Image Generation","Social Stereotypes","User Perception","Large Language Models","Human-Computer Interaction"],"dc:title":["Social stereotypes in text-to-image generation: Examining user perceptions and debiasing strategies"],"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"}