자료유형  

 학위논문

Control Number  

0017162393

International Standard Book Number  

9798384022596

Dewey Decimal Classification Number  

004

Main Entry-Personal Name  

Zhang, Li.

Publication, Distribution, etc. (Imprint  

[S.l.] : University of Pennsylvania., 2024

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2024

Physical Description  

164 p.

General Note  

Source: Dissertations Abstracts International, Volume: 86-02, Section: A.

General Note  

Advisor: Callison-Burch, Chris;Roth, Dan.

Dissertation Note  

Thesis (Ph.D.)--University of Pennsylvania, 2024.

Summary, Etc.  

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.

Subject Added Entry-Topical Term  

Computer science.

Subject Added Entry-Topical Term  

Information science.

Index Term-Uncontrolled  

Events and entities

Index Term-Uncontrolled  

Large language models

Index Term-Uncontrolled  

Machine learning

Index Term-Uncontrolled  

Natural language processing

Index Term-Uncontrolled  

Reasoning

Added Entry-Corporate Name  

University of Pennsylvania Computer and Information Science

Host Item Entry  

Dissertations Abstracts International. 86-02A.

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:654695