skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Understanding Causality with Large Language Models: Feasibility and Opportunities

arXiv.org, 2023-04

2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.2304.05524

Full text available

Citations Cited by
  • Title:
    Understanding Causality with Large Language Models: Feasibility and Opportunities
  • Author: Zhang, Cheng ; Bauer, Stefan ; Bennett, Paul ; Gao, Jiangfeng ; Gong, Wenbo ; Agrin Hilmkil ; Jennings, Joel ; Ma, Chao ; Minka, Tom ; Pawlowski, Nick ; Vaughan, James
  • Subjects: Computer Science - Computation and Language ; Computer Science - Learning ; Decision making ; Large language models ; Questions
  • Is Part Of: arXiv.org, 2023-04
  • Description: We assess the ability of large language models (LLMs) to answer causal questions by analyzing their strengths and weaknesses against three types of causal question. We believe that current LLMs can answer causal questions with existing causal knowledge as combined domain experts. However, they are not yet able to provide satisfactory answers for discovering new knowledge or for high-stakes decision-making tasks with high precision. We discuss possible future directions and opportunities, such as enabling explicit and implicit causal modules as well as deep causal-aware LLMs. These will not only enable LLMs to answer many different types of causal questions for greater impact but also enable LLMs to be more trustworthy and efficient in general.
  • Publisher: Ithaca: Cornell University Library, arXiv.org
  • Language: English
  • Identifier: EISSN: 2331-8422
    DOI: 10.48550/arxiv.2304.05524
  • Source: arXiv.org
    AUTh Library subscriptions: ProQuest Central
    Open Access: Freely Accessible Journals by multiple vendors
    ROAD: Directory of Open Access Scholarly Resources
Back to results list
Go to Previous pagePrevious Result  10 NextGo to Next page
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait