Structured Event Reasoning With Large Language Models

Guardado en:
Bibliografiske detaljer
Udgivet i:ProQuest Dissertations and Theses (2024)
Hovedforfatter: Zhang, Li
Udgivet:
ProQuest Dissertations & Theses
Fag:
Online adgang:Citation/Abstract
Full Text - PDF
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

MARC

LEADER 00000nab a2200000uu 4500
001 3098004806
003 UK-CbPIL
020 |a 9798384022596 
035 |a 3098004806 
045 2 |b d20240101  |b d20241231 
084 |a 66569  |2 nlm 
100 1 |a Zhang, Li 
245 1 |a Structured Event Reasoning With Large Language Models 
260 |b ProQuest Dissertations & Theses  |c 2024 
513 |a Dissertation/Thesis 
520 3 |a Reasoning 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. 
653 |a Computer science 
653 |a Artificial intelligence 
653 |a Information science 
773 0 |t ProQuest Dissertations and Theses  |g (2024) 
786 0 |d ProQuest  |t ProQuest Dissertations & Theses Global 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3098004806/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3098004806/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch