본문

서브메뉴

Building More Reliable and Scalable AI Systems with Foundation Model Programming
Building More Reliable and Scalable AI Systems with Foundation Model Programming
Building More Reliable and Scalable AI Systems with Foundation Model Programming

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202104746
ISBN  
9798290652214
DDC  
400
저자명  
Khattab, Omar Ahmed Metwally.
서명/저자  
Building More Reliable and Scalable AI Systems with Foundation Model Programming
발행사항  
[Sl] : Stanford University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
140 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: A.
주기사항  
Advisor: Manning, Christopher;Potts, Christopher;Zaharia, Matei.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2024.
초록/해제  
요약Language models (LMs), and more broadly foundation models, have made it much easier to prototype impressive AI demos, but turning these models into reliable and scalable AI systems remains challenging. Indeed, today's user-facing LMs often fabricate statements and make fundamental reasoning errors, while imposing enormous costs. We argue that the monolithic nature of LMs is what makes them hard to control, debug, and improve in modular and iterative ways when building AI systems.To address this, this dissertation introduces foundation model programming,a new paradigm centered on designing controllable systems that use LMs as modular fuzzy components and teach them the right system-level behavior via trial and error. To support this, we introduce (1) a new paradigm of information retrieval (IR) models by composing rich yet pruning-friendly interactions between token-level LM representations, (2) a new generation of scalable retrieval-based reasoning systems,and (3) a powerful compiler for natural language programming abstractions. We support these by proposing new algorithms for efficiently searching LM-based representations at scale, for weakly supervising natural language processing (NLP) systems with incomplete labels, and for optimizing the prompts of LMs inside arbitrary programs.This culminates in the ColBERTparadigm for neural IR and in the DSPyframework for natural language programming. We demonstrate through these contributions that making broad progress in AI is not restricted to training larger models, but can take the form of designing general toolsthat grant AI researchers and developers the capacity to controllably improve their systems via composition, to transparently ground their systems' responses in massive knowledge collections, and to scalably deploy their systems via new algorithms and new compositions of smaller LMs.
일반주제명  
Language
일반주제명  
Software
일반주제명  
Relevance
일반주제명  
Natural language processing
일반주제명  
Hallucinations
일반주제명  
Documents
일반주제명  
Retrieval performance measures
일반주제명  
Information retrieval
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-01A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017358751
■00520260202104746
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798290652214
■035    ▼a(MiAaPQ)AAI32149759
■035    ▼a(MiAaPQ)Stanfordzc625xj7842
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a400
■1001  ▼aKhattab,  Omar  Ahmed  Metwally.
■24510▼aBuilding  More  Reliable  and  Scalable  AI  Systems  with  Foundation  Model  Programming
■260    ▼a[Sl]▼bStanford  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a140  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  A.
■500    ▼aAdvisor:  Manning,  Christopher;Potts,  Christopher;Zaharia,  Matei.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2024.
■520    ▼aLanguage  models  (LMs),  and  more  broadly  foundation  models,  have  made  it  much  easier  to  prototype  impressive  AI  demos,  but  turning  these  models  into  reliable  and  scalable  AI  systems  remains  challenging.  Indeed,  today's  user-facing  LMs  often  fabricate  statements  and  make  fundamental  reasoning  errors,  while  imposing  enormous  costs.  We  argue  that  the  monolithic  nature  of  LMs  is  what  makes  them  hard  to  control,  debug,  and  improve  in  modular  and  iterative  ways  when  building  AI  systems.To  address  this,  this  dissertation  introduces  foundation  model  programming,a  new  paradigm  centered  on  designing  controllable  systems  that  use  LMs  as  modular  fuzzy  components  and  teach  them  the  right  system-level  behavior  via  trial  and  error.  To  support  this,  we  introduce  (1)  a  new  paradigm  of  information  retrieval  (IR)  models  by  composing  rich  yet  pruning-friendly  interactions  between  token-level  LM  representations,  (2)  a  new  generation  of  scalable  retrieval-based  reasoning  systems,and  (3)  a  powerful  compiler  for  natural  language  programming  abstractions.  We  support  these  by  proposing  new  algorithms  for  efficiently  searching  LM-based  representations  at  scale,  for  weakly  supervising  natural  language  processing  (NLP)  systems  with  incomplete  labels,  and  for  optimizing  the  prompts  of  LMs  inside  arbitrary  programs.This  culminates  in  the  ColBERTparadigm  for  neural  IR  and  in  the  DSPyframework  for  natural  language  programming.  We  demonstrate  through  these  contributions  that  making  broad  progress  in  AI  is  not  restricted  to  training  larger  models,  but  can  take  the  form  of  designing  general  toolsthat  grant  AI  researchers  and  developers  the  capacity  to  controllably  improve  their  systems  via  composition,  to  transparently  ground  their  systems'  responses  in  massive  knowledge  collections,  and  to  scalably  deploy  their  systems  via  new  algorithms  and  new  compositions  of  smaller  LMs.
■590    ▼aSchool  code:  0212.
■650  4▼aLanguage
■650  4▼aSoftware
■650  4▼aRelevance
■650  4▼aNatural  language  processing
■650  4▼aHallucinations
■650  4▼aDocuments
■650  4▼aRetrieval  performance  measures
■650  4▼aInformation  retrieval
■690    ▼a0679
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-01A.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358751▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF19345 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.