서브메뉴
검색
Broadening AI Access Through Human-Centered Natural Language Interfaces
Broadening AI Access Through Human-Centered Natural Language Interfaces
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202104857
- ISBN
- 9798288815591
- DDC
- 400
- 저자명
- Zhou, Kaitlyn.
- 서명/저자
- Broadening AI Access Through Human-Centered Natural Language Interfaces
- 발행사항
- [Sl] : Stanford University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 139 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
- 주기사항
- Advisor: Jurafsky, Dan.
- 학위논문주기
- Thesis (Ph.D.)--Stanford University, 2025.
- 초록/해제
- 요약As natural language becomes the default interface for human-AI interaction, questions arise on how to design large language models (LLMs) to safely support a range of human tasks. In this dissertation, I present three lines of work that contribute to our understanding and design of natural language interfaces, taking the perspective that the safe design of LLMs is not only a technical problem, but one that involves the consideration of human factors. First, I investigate the key safety risks of LLMs in their ability to communicate risk and limitations to humans, finding that LLMs struggle both to interpret and generate expressions of certainty correctly. Next, I propose a new evaluation framework to understand the potential harms of human-LM interactions, emphasizing the need to evaluate the behaviors triggered by generated language rather than the language quality itself. Lastly, I explore the ways in which NLP research could support the needs of a broader user audience, advocating for the introduction of tasks and needs previously overlooked in our literature. Together, my work identifies new safety risks, reveals mitigation solutions, proposes a new evaluation framework, and expands our understanding of how LLMs could be used to safely support the needs of a broader user audience.
- 일반주제명
- Language
- 일반주제명
- User needs
- 일반주제명
- Toxicity
- 일반주제명
- Confidence
- 일반주제명
- False information
- 일반주제명
- Linguistics
- 일반주제명
- Hallucinations
- 일반주제명
- Large language models
- 일반주제명
- Computer science
- 키워드
- Expressions
- 기타저자
- Stanford University.
- 기본자료저록
- Dissertations Abstracts International. 87-02B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359262
■00520260202104857
■006m o d
■007cr#unu||||||||
■020 ▼a9798288815591
■035 ▼a(MiAaPQ)AAI32201026
■035 ▼a(MiAaPQ)Stanfordxw505rd7683
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a400
■1001 ▼aZhou, Kaitlyn.
■24510▼aBroadening AI Access Through Human-Centered Natural Language Interfaces
■260 ▼a[Sl]▼bStanford University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a139 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-02, Section: B.
■500 ▼aAdvisor: Jurafsky, Dan.
■5021 ▼aThesis (Ph.D.)--Stanford University, 2025.
■520 ▼aAs natural language becomes the default interface for human-AI interaction, questions arise on how to design large language models (LLMs) to safely support a range of human tasks. In this dissertation, I present three lines of work that contribute to our understanding and design of natural language interfaces, taking the perspective that the safe design of LLMs is not only a technical problem, but one that involves the consideration of human factors. First, I investigate the key safety risks of LLMs in their ability to communicate risk and limitations to humans, finding that LLMs struggle both to interpret and generate expressions of certainty correctly. Next, I propose a new evaluation framework to understand the potential harms of human-LM interactions, emphasizing the need to evaluate the behaviors triggered by generated language rather than the language quality itself. Lastly, I explore the ways in which NLP research could support the needs of a broader user audience, advocating for the introduction of tasks and needs previously overlooked in our literature. Together, my work identifies new safety risks, reveals mitigation solutions, proposes a new evaluation framework, and expands our understanding of how LLMs could be used to safely support the needs of a broader user audience.
■590 ▼aSchool code: 0212.
■650 4▼aLanguage
■650 4▼aUser needs
■650 4▼aToxicity
■650 4▼aConfidence
■650 4▼aFalse information
■650 4▼aNatural language processing
■650 4▼aLinguistics
■650 4▼aHallucinations
■650 4▼aLarge language models
■650 4▼aComputer science
■653 ▼aLarge language models
■653 ▼aExpressions
■653 ▼aNatural language interfaces
■690 ▼a0290
■690 ▼a0679
■690 ▼a0984
■690 ▼a0800
■71020▼aStanford University.
■7730 ▼tDissertations Abstracts International▼g87-02B.
■790 ▼a0212
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359262▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
