Table and Knowledge Graph Augmented Question Answering with Large Language Models
Retrieval augmented generation (RAG) with Large Language Models (LLMs) has attracted wide attention, as its strengths for addressing the issues of LLMs such as failure to support changes, hallucination, shortage of explanation, etc. The report will introduce some recent works on using tables and knowledge graphs as sources for supporting RAG for question answering (QA), including effective methods based on structured data rewriting, and novel resources for benchmarking knowledge incompleteness, knowledge poisoning, and attributed QA.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
Loading virtual attendance info...
- Contact Event Host
-
m.garcia-constantino@ulster.ac.uk
- Co-sponsored by Ulster University
Speakers
Jiaoyan of University of Manchester, UK
Table and Knowledge Graph Augmented Question Answering with Large Language Models
Retrieval augmented generation (RAG) with Large Language Models (LLMs) has attracted wide attention, as its strengths for addressing the issues of LLMs such as failure to support changes, hallucination, shortage of explanation, etc. The report will introduce some recent works on using tables and knowledge graphs as sources for supporting RAG for question answering (QA), including effective methods based on structured data rewriting, and novel resources for benchmarking knowledge incompleteness, knowledge poisoning, and attributed QA.
Biography:
Dr. Jiaoyan Chen is Senior Lecturer (Associate Professor) in Department of Computer Science, The University of Manchester. Before joining The University of Manchester in 2022, he worked as a Senior Researcher in University of Oxford since 2017 and got his PhD in Computer Science and Technology in Zhejiang University. Jiaoyan's research focuses on Knowledge Graph, Ontology, Knowledge and Data Management, Semantic Web and Artificial Intelligence. Home page: https://chenjiaoyan.github.io/.