서브메뉴
검색
Structured Event Reasoning With Large Language Models
Structured Event Reasoning With Large Language Models
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152007
- ISBN
- 9798384022596
- DDC
- 004
- 저자명
- Zhang, Li.
- 서명/저자
- Structured Event Reasoning With Large Language Models
- 발행사항
- [Sl] : University of Pennsylvania, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 164 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-02, Section: A.
- 주기사항
- Advisor: Callison-Burch, Chris;Roth, Dan.
- 학위논문주기
- Thesis (Ph.D.)--University of Pennsylvania, 2024.
- 초록/해제
- 요약Reasoning about real-life events is a unifying challenge in AI and NLP that has profound utility in a variety of domains, while fallacy in high-stake applications could be catastrophic. Able to work with diverse text in these domains, large language models (LLMs) have proven capable of answering questions and solving problems. However, I show that end-to-end LLMs still systematically fail to reason about complex events, and they lack interpretability due to their black-box nature. To address these issues, I propose three general approaches to use LLMs in conjunction with a structured representation of events. The first is a language-based representation involving relations of sub-events that can be learned by LLMs via fine-tuning. The second is a semi-symbolic representation involving states of entities that can be predicted and leveraged by LLMs via few-shot prompting. The third is a fully symbolic representation that can be predicted by LLMs trained with structured data and be executed by symbolic solvers. On a suite of event reasoning tasks spanning common-sense inference and planning, I show that each approach greatly outperforms end-to-end LLMs with more interpretability. These results suggest manners of synergy between LLMs and structured representations for event reasoning and beyond.
- 일반주제명
- Computer science
- 일반주제명
- Information science
- 키워드
- Machine learning
- 키워드
- Reasoning
- 기타저자
- University of Pennsylvania Computer and Information Science
- 기본자료저록
- Dissertations Abstracts International. 86-02A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017162393
■00520250211152007
■006m o d
■007cr#unu||||||||
■020 ▼a9798384022596
■035 ▼a(MiAaPQ)AAI31330733
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aZhang, Li.
■24510▼aStructured Event Reasoning With Large Language Models
■260 ▼a[Sl]▼bUniversity of Pennsylvania▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a164 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-02, Section: A.
■500 ▼aAdvisor: Callison-Burch, Chris;Roth, Dan.
■5021 ▼aThesis (Ph.D.)--University of Pennsylvania, 2024.
■520 ▼aReasoning about real-life events is a unifying challenge in AI and NLP that has profound utility in a variety of domains, while fallacy in high-stake applications could be catastrophic. Able to work with diverse text in these domains, large language models (LLMs) have proven capable of answering questions and solving problems. However, I show that end-to-end LLMs still systematically fail to reason about complex events, and they lack interpretability due to their black-box nature. To address these issues, I propose three general approaches to use LLMs in conjunction with a structured representation of events. The first is a language-based representation involving relations of sub-events that can be learned by LLMs via fine-tuning. The second is a semi-symbolic representation involving states of entities that can be predicted and leveraged by LLMs via few-shot prompting. The third is a fully symbolic representation that can be predicted by LLMs trained with structured data and be executed by symbolic solvers. On a suite of event reasoning tasks spanning common-sense inference and planning, I show that each approach greatly outperforms end-to-end LLMs with more interpretability. These results suggest manners of synergy between LLMs and structured representations for event reasoning and beyond.
■590 ▼aSchool code: 0175.
■650 4▼aComputer science
■650 4▼aInformation science
■653 ▼aEvents and entities
■653 ▼aLarge language models
■653 ▼aMachine learning
■653 ▼aNatural language processing
■653 ▼aReasoning
■690 ▼a0984
■690 ▼a0723
■690 ▼a0800
■71020▼aUniversity of Pennsylvania▼bComputer and Information Science.
■7730 ▼tDissertations Abstracts International▼g86-02A.
■790 ▼a0175
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162393▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
