본문

서브메뉴

Dialogue Systems Specialized in Social Influence: Systems, Methods, and Ethics- [electronic resource]
Dialogue Systems Specialized in Social Influence: Systems, Methods, and Ethics - [electron...
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  
Human-computer interaction
키워드  
Natural Language Processing
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

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF05704 전자도서 마이폴더 부재도서신고 비도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.