東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Human-Ai Interaction Under Societal ...

Gordon, Mitchell Louis.

FindBook

Google Book

Amazon

博客來

Human-Ai Interaction Under Societal Disagreement.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Human-Ai Interaction Under Societal Disagreement./
作者:	Gordon, Mitchell Louis.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	132 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-06, Section: A.
Contained By:	Dissertations Abstracts International85-06A.
標題:	Juries. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30726818
ISBN:	9798381018110

Human-Ai Interaction Under Societal Disagreement.
Gordon, Mitchell Louis.

Human-Ai Interaction Under Societal Disagreement. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 132 p.

Source: Dissertations Abstracts International, Volume: 85-06, Section: A.

Thesis (Ph.D.)--Stanford University, 2023.

This item must not be sold to any third party vendors.

Whose voices - whose labels - should a machine learning algorithm learn to emulate? For AI tasks ranging from online comment toxicity detection to poster design to medical treatment, different groups in society may have irreconcilable disagreements about what constitutes ground truth. Today's supervised machine learning pipeline typically resolves these disagreements implicitly by majority vote over annotators' opinions. This majoritarian procedure abstracts individual people out of the pipeline and collapses their labels into an aggregate pseudo-human, ignoring minority groups' labels.In this dissertation, I will present Jury Learning: an interactive AI architecture that enables developers to explicitly reason over whose voice a model ought to emulate through the metaphor of a jury. Through my exploratory interface, practitioners can declaratively define which people or groups, in what proportion, determine the classifier's prediction. To evaluate models under societal disagreement, I will also present The Disagreement Deconvolution: a metric transformation showing how, in abstracting away the individual people that models impact, current metrics dramatically overstate the performance of many user-facing tasks. These components become building blocks of a new pipeline for encoding our goals and values in human-AI systems, which strives to bridge principles of HCI with the realities of machine learning.

ISBN: 9798381018110Subjects--Topical Terms:

3702750
Juries.

Human-Ai Interaction Under Societal Disagreement.
LDR:02556nmm a2200361 4500 001 2396927
005 20240618081821.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798381018110
035 $a (MiAaPQ)AAI30726818
035 $a (MiAaPQ)STANFORDxf168rn2553
035 $a AAI30726818
040 $a MiAaPQ $c MiAaPQ
100 1 $a Gordon, Mitchell Louis. $3 3766687
245 1 0 $a Human-Ai Interaction Under Societal Disagreement.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 132 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-06, Section: A.
500 $a Advisor: Landay, James;Hashimoto, Tatsunori;Bernstein, Michael.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
506 $a This item must not be sold to any third party vendors.
520 $a Whose voices - whose labels - should a machine learning algorithm learn to emulate? For AI tasks ranging from online comment toxicity detection to poster design to medical treatment, different groups in society may have irreconcilable disagreements about what constitutes ground truth. Today's supervised machine learning pipeline typically resolves these disagreements implicitly by majority vote over annotators' opinions. This majoritarian procedure abstracts individual people out of the pipeline and collapses their labels into an aggregate pseudo-human, ignoring minority groups' labels.In this dissertation, I will present Jury Learning: an interactive AI architecture that enables developers to explicitly reason over whose voice a model ought to emulate through the metaphor of a jury. Through my exploratory interface, practitioners can declaratively define which people or groups, in what proportion, determine the classifier's prediction. To evaluate models under societal disagreement, I will also present The Disagreement Deconvolution: a metric transformation showing how, in abstracting away the individual people that models impact, current metrics dramatically overstate the performance of many user-facing tasks. These components become building blocks of a new pipeline for encoding our goals and values in human-AI systems, which strives to bridge principles of HCI with the realities of machine learning.
590 $a School code: 0212.
650 4 $a Juries. $3 3702750
650 4 $a Computer science. $3 523869
650 4 $a Content management. $3 3766688
650 4 $a Recommender systems. $3 3562220
650 4 $a Decision making. $3 517204
650 4 $a Society. $3 700566
650 4 $a False information. $3 3564362
650 4 $a Chatbots. $3 3705435
650 4 $a Information science. $3 554358
690 $a 0984
690 $a 0800
690 $a 0723
690 $a 0454
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 85-06A.
790 $a 0212
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30726818