본문

서브메뉴

Extracting Knowledge with Multimodal and Multilingual Intelligent Systems
Extracting Knowledge with Multimodal and Multilingual Intelligent Systems
Extracting Knowledge with Multimodal and Multilingual Intelligent Systems

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105550
ISBN  
9798265401205
DDC  
496
저자명  
Chen, Yang.
서명/저자  
Extracting Knowledge with Multimodal and Multilingual Intelligent Systems
발행사항  
[Sl] : Georgia Institute of Technology, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
196 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Ritter, Alan;Xu, Wei.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2024.
초록/해제  
요약Recent advancements in large language models (LLMs) have revolutionized natural language processing and vision-language tasks. While demonstrating emergent capabilities, these models present challenges in responsible development, particularly in visual world knowledge, privacy concerns, and multilingual capabilities. This thesis addresses these challenges through three main contributions. First, we introduce InfoSeek, a vision-language benchmark assessing models' ability to leverage world knowledge for answering queries about visual entities. To improve performance on this challenging task, we develop multimodal retrieval-augmented generation systems to acquire knowledge from external resources. Inspired by the visual knowledge we found from InfoSeek, we raise an emergent privacy concern of multimodal LLM to reveal geolocation information of user posted images. We then present PrivQA, a benchmark evaluating models' ability to follow access control instructions and prevent private information disclosure. Our findings reveal biases and vulnerabilities in current privacy protection mechanisms, especially in adversarial settings. Third, we propose three approaches to enhance multilingual capabilities and improve information extraction (IE) in low-resource languages: TransFusion, a framework leveraging English translations to enhance multilingual performance; EasyProject, a simplified method for creating synthetic multilingual IE data; and a model selection algorithm predicting multilingual model performance on unseen languages. These contributions aim to develop and benchmark methods for extracting knowledge with multimodal and multilingual intelligent systems, addressing key challenges in emergent visual knowledge, privacy concerns, and multilingual capabilities.
일반주제명  
African languages
일반주제명  
Multilingualism
일반주제명  
Privacy
일반주제명  
Large language models
일반주제명  
Bilingualism
일반주제명  
Access control
일반주제명  
Labeling
일반주제명  
Bilingual education
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017360580
■00520260202105550
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265401205
■035    ▼a(MiAaPQ)AAI32315679
■035    ▼a(MiAaPQ)GeorgiaTech75688
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a496
■1001  ▼aChen,  Yang.
■24510▼aExtracting  Knowledge  with  Multimodal  and  Multilingual  Intelligent  Systems
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a196  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Ritter,  Alan;Xu,  Wei.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2024.
■520    ▼aRecent  advancements  in  large  language  models  (LLMs)  have  revolutionized  natural  language  processing  and  vision-language  tasks.  While  demonstrating  emergent  capabilities,  these  models  present  challenges  in  responsible  development,  particularly  in  visual  world  knowledge,  privacy  concerns,  and  multilingual  capabilities.  This  thesis  addresses  these  challenges  through  three  main  contributions.  First,  we  introduce  InfoSeek,  a  vision-language  benchmark  assessing  models'  ability  to  leverage  world  knowledge  for  answering  queries  about  visual  entities.  To  improve  performance  on  this  challenging  task,  we  develop  multimodal  retrieval-augmented  generation  systems  to  acquire  knowledge  from  external  resources.  Inspired  by  the  visual  knowledge  we  found  from  InfoSeek,  we  raise  an  emergent  privacy  concern  of  multimodal  LLM  to  reveal  geolocation  information  of  user  posted  images.  We  then  present  PrivQA,  a  benchmark  evaluating  models'  ability  to  follow  access  control  instructions  and  prevent  private  information  disclosure.  Our  findings  reveal  biases  and  vulnerabilities  in  current  privacy  protection  mechanisms,  especially  in  adversarial  settings.  Third,  we  propose  three  approaches  to  enhance  multilingual  capabilities  and  improve  information  extraction  (IE)  in  low-resource  languages:  TransFusion,  a  framework  leveraging  English  translations  to  enhance  multilingual  performance;  EasyProject,  a  simplified  method  for  creating  synthetic  multilingual  IE  data;  and  a  model  selection  algorithm  predicting  multilingual  model  performance  on  unseen  languages.  These  contributions  aim  to  develop  and  benchmark  methods  for  extracting  knowledge  with  multimodal  and  multilingual  intelligent  systems,  addressing  key  challenges  in  emergent  visual  knowledge,  privacy  concerns,  and  multilingual  capabilities.
■590    ▼aSchool  code:  0078.
■650  4▼aAfrican  languages
■650  4▼aMultilingualism
■650  4▼aPrivacy
■650  4▼aLarge  language  models
■650  4▼aBilingualism
■650  4▼aAccess  control
■650  4▼aLabeling
■650  4▼aBilingual  education
■690    ▼a0800
■690    ▼a0282
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360580▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

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
    TF14962 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

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

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.