國立虎尾科技大學 |

Towards Effective and Inclusive AI: Aligning AI Systems With User Needs and Stakeholder Values Across Diverse Contexts /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Towards Effective and Inclusive AI: Aligning AI Systems With User Needs and Stakeholder Values Across Diverse Contexts // Yang Trista Cao.
作者:	Cao, Yang Trista,
面頁冊數:	1 electronic resource (301 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-01, Section: A.
Contained By:	Dissertations Abstracts International86-01A.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31149399
ISBN:	9798383181850

Towards Effective and Inclusive AI: Aligning AI Systems With User Needs and Stakeholder Values Across Diverse Contexts /
Cao, Yang Trista,

Towards Effective and Inclusive AI: Aligning AI Systems With User Needs and Stakeholder Values Across Diverse Contexts /Yang Trista Cao. - 1 electronic resource (301 pages)

Source: Dissertations Abstracts International, Volume: 86-01, Section: A.

Inspired by the Turing test, a long line of research in AI has focused on technical improvement on tasks thought to require human-like comprehension. However, this focus has often resulted in models with impressive technical capabilities but uncertain real-world applicability. Despite the advancements of large pre-trained models, we still see various failure cases towards discriminated groups and when applied to specific applications. A major problem here is the detached model development process - these models are designed, developed, and evaluated with limited consideration of their users and stakeholders. My dissertation is dedicated to addressing this detachment by examining how artificial intelligence (AI) systems can be more effectively aligned with the needs of users and the values of stakeholders across diverse contexts. This work aims to close the gap between the current state of AI technology and its meaningful application in the lives of real-life stakeholders.My thesis explores three key aspects of aligning AI systems with human needs and values: identifying sources of misalignment, addressing the needs of specific user groups, and ensuring value alignment across diverse stakeholders. First, I examine potential causes of misalignment in AI system development, focusing on gender biases in natural language processing (NLP) systems. I demonstrate that without careful consideration of real-life stakeholders, AI systems are prone to biases entering at each development stage. Second, I explore the alignment of AI systems for specific user groups by analyzing two real-life application contexts: a content moderation assistance system for volunteer moderators and a visual question answering (VQA) system for blind and visually impaired (BVI) individuals. In both contexts, I identify significant gaps in AI systems and provide directions for better alignment with users' needs. Finally, I assess the alignment of AI systems with human values, focusing on stereotype issues within general large language models (LLMs). I propose a theory-grounded method for systematically evaluating stereotypical associations and exploring their impact on diverse user identities, including intersectional identity stereotypes and the leakage of stereotypes across cultures.Through these investigations, this dissertation contributes to the growing field of human-centered AI by providing insights, methodologies, and recommendations for aligning AI systems with the needs and values of diverse stakeholders. By addressing the challenges of misalignment, user-specific needs, and value alignment, this work aims to foster the development of AI technologies that effectively collaborate with and empower users while promoting fairness, inclusivity, and positive social impact.

English

ISBN: 9798383181850Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Alignment

Towards Effective and Inclusive AI: Aligning AI Systems With User Needs and Stakeholder Values Across Diverse Contexts /
LDR:04310nam a22004213i 4500 001 1157764
005 20250603111411.5
006 m o d
007 cr|nu||||||||
008 250804s2024 miu||||||m |||||||eng d
020 $a 9798383181850
035 $a (MiAaPQD)AAI31149399
035 $a AAI31149399
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Cao, Yang Trista, $e author. $3 1484031
245 1 0 $a Towards Effective and Inclusive AI: Aligning AI Systems With User Needs and Stakeholder Values Across Diverse Contexts / $c Yang Trista Cao.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (301 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-01, Section: A.
500 $a Advisors: Daume, Hal, III Committee members: Kacorri, Hernisa; Shilton, Katie; Rudinger, Rachel; Chang, Kai-Wei.
502 $b Ph.D. $c University of Maryland, College Park $d 2024.
520 $a Inspired by the Turing test, a long line of research in AI has focused on technical improvement on tasks thought to require human-like comprehension. However, this focus has often resulted in models with impressive technical capabilities but uncertain real-world applicability. Despite the advancements of large pre-trained models, we still see various failure cases towards discriminated groups and when applied to specific applications. A major problem here is the detached model development process - these models are designed, developed, and evaluated with limited consideration of their users and stakeholders. My dissertation is dedicated to addressing this detachment by examining how artificial intelligence (AI) systems can be more effectively aligned with the needs of users and the values of stakeholders across diverse contexts. This work aims to close the gap between the current state of AI technology and its meaningful application in the lives of real-life stakeholders.My thesis explores three key aspects of aligning AI systems with human needs and values: identifying sources of misalignment, addressing the needs of specific user groups, and ensuring value alignment across diverse stakeholders. First, I examine potential causes of misalignment in AI system development, focusing on gender biases in natural language processing (NLP) systems. I demonstrate that without careful consideration of real-life stakeholders, AI systems are prone to biases entering at each development stage. Second, I explore the alignment of AI systems for specific user groups by analyzing two real-life application contexts: a content moderation assistance system for volunteer moderators and a visual question answering (VQA) system for blind and visually impaired (BVI) individuals. In both contexts, I identify significant gaps in AI systems and provide directions for better alignment with users' needs. Finally, I assess the alignment of AI systems with human values, focusing on stereotype issues within general large language models (LLMs). I propose a theory-grounded method for systematically evaluating stereotypical associations and exploring their impact on diverse user identities, including intersectional identity stereotypes and the leakage of stereotypes across cultures.Through these investigations, this dissertation contributes to the growing field of human-centered AI by providing insights, methodologies, and recommendations for aligning AI systems with the needs and values of diverse stakeholders. By addressing the challenges of misalignment, user-specific needs, and value alignment, this work aims to foster the development of AI technologies that effectively collaborate with and empower users while promoting fairness, inclusivity, and positive social impact.
546 $a English
590 $a School code: 0117
650 4 $a Computer science. $3 573171
650 4 $a Linguistics. $3 557829
653 $a Alignment
653 $a Content moderation
653 $a Fairness
653 $a Natural language processing
690 $a 0984
690 $a 0800
690 $a 0290
710 2 $a University of Maryland, College Park. $b Computer Science. $3 1180862
720 1 $a Daume, Hal, III $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-01A.
790 $a 0117
791 $a Ph.D.
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31149399