서브메뉴
검색
Dialogue Systems Specialized in Social Influence: Systems, Methods, and Ethics- [electronic resource]
Dialogue Systems Specialized in Social Influence: Systems, Methods, and Ethics- [electronic resource]
상세정보
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214101519
- ISBN
- 9798379918453
- DDC
- 004
- 저자명
- Shi, Weiyan.
- 서명/저자
- Dialogue Systems Specialized in Social Influence: Systems, Methods, and Ethics - [electronic resource]
- 발행사항
- [S.l.]: : Columbia University., 2023
- 발행사항
- Ann Arbor : : ProQuest Dissertations & Theses,, 2023
- 형태사항
- 1 online resource(174 p.)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-01, Section: A.
- 주기사항
- Advisor: Yu, Zhou.
- 학위논문주기
- Thesis (Ph.D.)--Columbia University, 2023.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 초록/해제
- 요약This thesis concerns the task of how to develop dialogue systems specialized in social influence and problems around deploying such systems. Dialogue systems have become widely adopted in our daily life. Most dialogue systems are primarily focused on information-seeking tasks or social companionship. However, they cannot apply strategies in complex and critical social influence tasks, such as healthy habit promotion, emotional support, etc. In this work, we formally define social influence dialogue systems to be systems that influence users' behaviors, feelings, thoughts, or opinions through natural conversations. We also present methods to make such systems intelligible, privacy-preserving, and thus deployable in real life. Finally, we acknowledge potential ethical issues around social influence systems and propose solutions to mitigate them in Chapter 6.Social influence dialogues span various domains, such as persuasion, negotiation, and recommendation. We first propose a donation persuasion task, PERSUASIONFORGOOD, and ground our study on this persuasion task for social good. We then build a persuasive dialogue system, by refining the dialogue model for intelligibility and imitating human experts for persuasiveness, and a negotiation agent that can play the game of Diplomacy by decoupling the planning engine and the dialogue generation module to improve controllability of social influence systems. To deploy such a system in the wild, our work examines how humans perceive the AI agent's identity, and how their perceptions impact the social influence outcome. Moreover, dialogue models are trained on conversations, where people could share personal information. This creates privacy concerns for deployment as the models may memorize private information. To protect user privacy in the training data, our work develops privacy-preserving learning algorithms to ensure deployed models are safe under privacy attacks. Finally, deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves. So we propose JUICER, a framework to make use of both binary and free-form textual human feedback to augment the training data and keep improving dialogue model performance after deployment. Building social influence dialogue systems enables us to research future expert-level AI systems that are accessible via natural languages, accountable with domain knowledge, and privacy-preserving with privacy guarantees.
- 일반주제명
- Computer science.
- 일반주제명
- Web studies.
- 일반주제명
- Information technology.
- 키워드
- Dialogue systems
- 키워드
- Privacy
- 키워드
- Social influence
- 기타저자
- Columbia University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 85-01A.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008240612s2023 us |||||||||||||||c||eng d■001000016934019
■00520240214101519
■006m o d
■007cr#unu||||||||
■020 ▼a9798379918453
■035 ▼a(MiAaPQ)AAI30569707
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aShi, Weiyan.
■24510▼aDialogue Systems Specialized in Social Influence: Systems, Methods, and Ethics▼h[electronic resource]
■260 ▼a[S.l.]:▼bColumbia University. ▼c2023
■260 1▼aAnn Arbor :▼bProQuest Dissertations & Theses, ▼c2023
■300 ▼a1 online resource(174 p.)
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-01, Section: A.
■500 ▼aAdvisor: Yu, Zhou.
■5021 ▼aThesis (Ph.D.)--Columbia University, 2023.
■506 ▼aThis item must not be sold to any third party vendors.
■520 ▼aThis thesis concerns the task of how to develop dialogue systems specialized in social influence and problems around deploying such systems. Dialogue systems have become widely adopted in our daily life. Most dialogue systems are primarily focused on information-seeking tasks or social companionship. However, they cannot apply strategies in complex and critical social influence tasks, such as healthy habit promotion, emotional support, etc. In this work, we formally define social influence dialogue systems to be systems that influence users' behaviors, feelings, thoughts, or opinions through natural conversations. We also present methods to make such systems intelligible, privacy-preserving, and thus deployable in real life. Finally, we acknowledge potential ethical issues around social influence systems and propose solutions to mitigate them in Chapter 6.Social influence dialogues span various domains, such as persuasion, negotiation, and recommendation. We first propose a donation persuasion task, PERSUASIONFORGOOD, and ground our study on this persuasion task for social good. We then build a persuasive dialogue system, by refining the dialogue model for intelligibility and imitating human experts for persuasiveness, and a negotiation agent that can play the game of Diplomacy by decoupling the planning engine and the dialogue generation module to improve controllability of social influence systems. To deploy such a system in the wild, our work examines how humans perceive the AI agent's identity, and how their perceptions impact the social influence outcome. Moreover, dialogue models are trained on conversations, where people could share personal information. This creates privacy concerns for deployment as the models may memorize private information. To protect user privacy in the training data, our work develops privacy-preserving learning algorithms to ensure deployed models are safe under privacy attacks. Finally, deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves. So we propose JUICER, a framework to make use of both binary and free-form textual human feedback to augment the training data and keep improving dialogue model performance after deployment. Building social influence dialogue systems enables us to research future expert-level AI systems that are accessible via natural languages, accountable with domain knowledge, and privacy-preserving with privacy guarantees.
■590 ▼aSchool code: 0054.
■650 4▼aComputer science.
■650 4▼aWeb studies.
■650 4▼aInformation technology.
■653 ▼aDialogue systems
■653 ▼aHuman-computer interaction
■653 ▼aNatural Language Processing
■653 ▼aPrivacy
■653 ▼aSocial influence
■690 ▼a0984
■690 ▼a0800
■690 ▼a0489
■690 ▼a0646
■71020▼aColumbia University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g85-01A.
■773 ▼tDissertation Abstract International
■790 ▼a0054
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16934019▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202402▼f2024


