본문

서브메뉴

Efficient and Robust Web Scale Language Model Based Retrieval, Generation, and Understanding
Efficient and Robust Web Scale Language Model Based Retrieval, Generation, and Understandi...
Efficient and Robust Web Scale Language Model Based Retrieval, Generation, and Understanding

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260209102846
ISBN  
9798291562574
DDC  
004
저자명  
Campos, Daniel.
서명/저자  
Efficient and Robust Web Scale Language Model Based Retrieval, Generation, and Understanding
발행사항  
[Sl] : University of Illinois at Urbana-Champaign, 2023
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2023
형태사항  
203 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: Zhai, Cheng Xiang.
학위논문주기  
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
초록/해제  
요약Large language models effectively generate contextualized word representations across languages, domains, and tasks. Drive by these abilities, these models have become a building staple for many researchers and engineers who use text as their medium of representation, much like concrete is a staple in the construction world. Via the broad study and implementation, problems with large models have come to light: they can be expensive, brittle to noise, and produce unwanted outputs. Their large size and computational overhead make them difficult and costly to deploy and use for inference. Minor variations in text inputs, such as typos or misspellings, can cause significant losses in model accuracy. Seeking to improve how these models can be used for real world usage and deployments, this thesis focuses on approaches for improving performance by compressing, hardening, and optimizing models' performance based on deployment needs. To explore the challenges with largescale deployments concerning robustness and inference efficiency, we explore four commonly used language workloads: textual understanding and classification, passage retrieval, and text generation. We chose these broad but connected tasks to ensure that our compression approaches broadly apply to natural language processing. First, we propose a general framework for improving model inference on broad language understanding workloads by studying how unstructured pruning, structured pruning, and quantization can be leveraged to compress models and improve inference speeds. Second, we examine how models can be deployed for usage in web-scale generation and understanding workloads. Leveraging multi-task modeling, asymmetrical pruning, knowledge distillation, and quantization allows for cost-efficient scaling to web-scale workloads. Third, we explore methods of tuning and optimizing dense retrieval methods post-training to ensure they perform well on real-world data. Our experiments yield simple and effective ways of increasing model robustness and decreasing inference costs without any need for retraining or index re-generation. Finally, we discuss future work, focusing on sequential compression approaches to sequence LLMs to allow generative workloads to reach web-scale deployments.
일반주제명  
Computer science
일반주제명  
Computer engineering
키워드  
Efficient inference
키워드  
Large language models
키워드  
Semantic retrieval
키워드  
Web-scale inference
기타저자  
University of Illinois at Urbana-Champaign Computer Science
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260203s2023        us                              c    eng  d
■001000017365880
■00520260209102846
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798291562574
■035    ▼a(MiAaPQ)AAI32271292
■035    ▼a(MiAaPQ)httphdlhandlenet2142121494
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aCampos,  Daniel.
■24510▼aEfficient  and  Robust  Web  Scale  Language  Model  Based  Retrieval,  Generation,  and  Understanding
■260    ▼a[Sl]▼bUniversity  of  Illinois  at  Urbana-Champaign▼c2023
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2023
■300    ▼a203  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  Zhai,  Cheng  Xiang.
■5021  ▼aThesis  (Ph.D.)--University  of  Illinois  at  Urbana-Champaign,  2023.
■520    ▼aLarge  language  models  effectively  generate  contextualized  word  representations  across  languages,  domains,  and  tasks.  Drive  by  these  abilities,  these  models  have  become  a  building  staple  for  many  researchers  and  engineers  who  use  text  as  their  medium  of  representation,  much  like  concrete  is  a  staple  in  the  construction  world.  Via  the  broad  study  and  implementation,  problems  with  large  models  have  come  to  light:  they  can  be  expensive,  brittle  to  noise,  and  produce  unwanted  outputs.  Their  large  size  and  computational  overhead  make  them  difficult  and  costly  to  deploy  and  use  for  inference.  Minor  variations  in  text  inputs,  such  as  typos  or  misspellings,  can  cause  significant  losses  in  model  accuracy.  Seeking  to  improve  how  these  models  can  be  used  for  real  world  usage  and  deployments,  this  thesis  focuses  on  approaches  for  improving  performance  by  compressing,  hardening,  and  optimizing  models'  performance  based  on  deployment  needs.  To  explore  the  challenges  with  largescale  deployments  concerning  robustness  and  inference  efficiency,  we  explore  four  commonly  used  language  workloads:  textual  understanding  and  classification,  passage  retrieval,  and  text  generation.  We  chose  these  broad  but  connected  tasks  to  ensure  that  our  compression  approaches  broadly  apply  to  natural  language  processing.  First,  we  propose  a  general  framework  for  improving  model  inference  on  broad  language  understanding  workloads  by  studying  how  unstructured  pruning,  structured  pruning,  and  quantization  can  be  leveraged  to  compress  models  and  improve  inference  speeds.  Second,  we  examine  how  models  can  be  deployed  for  usage  in  web-scale  generation  and  understanding  workloads.  Leveraging  multi-task  modeling,  asymmetrical  pruning,  knowledge  distillation,  and  quantization  allows  for  cost-efficient  scaling  to  web-scale  workloads.  Third,  we  explore  methods  of  tuning  and  optimizing  dense  retrieval  methods  post-training  to  ensure  they  perform  well  on  real-world  data.  Our  experiments  yield  simple  and  effective  ways  of  increasing  model  robustness  and  decreasing  inference  costs  without  any  need  for  retraining  or  index  re-generation.  Finally,  we  discuss  future  work,  focusing  on  sequential  compression  approaches  to  sequence  LLMs  to  allow  generative  workloads  to  reach  web-scale  deployments.
■590    ▼aSchool  code:  0090.
■650  4▼aComputer  science
■650  4▼aComputer  engineering
■653    ▼aEfficient  inference
■653    ▼aLarge  language  models
■653    ▼aSemantic  retrieval
■653    ▼aWeb-scale  inference
■690    ▼a0984
■690    ▼a0464
■690    ▼a0800
■71020▼aUniversity  of  Illinois  at  Urbana-Champaign▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0090
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365880▼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
    TF18986 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.