Skip to main navigation
Skip to search
Skip to main content
University of Edinburgh Research Explorer Home
Help & FAQ
Home
Research output
Profiles
Research units
Projects
Datasets
Prizes
Activities
Press/Media
Equipment
Search by expertise, name or affiliation
View Scopus Profile
Jeff Pan
PROF
Personal Chair of Knowledge Computing
,
School of Informatics
Institute of Language, Cognition and Computation
Language, Interaction, and Robotics
https://orcid.org/0000-0002-9779-2088
Overview
Fingerprint
Network
Research output
(236)
Activities
(3)
Projects
(4)
Similar Profiles
(6)
Research output
180
Conference contribution
33
Article
12
Chapter
4
Chapter (peer-reviewed)
7
More
4
Preprint
1
Other chapter contribution
1
Other
1
Paper
Research output per year
Research output per year
4 results
Publication Year, Title
(descending)
Publication Year, Title
(ascending)
Title
Type
Filter
Preprint
Search results
2024
Large language models as reliable knowledge bases?
Zheng, D.,
Lapata, M.
&
Pan, J. Z.
,
18 Jul 2024
,
ArXiv
.
Research output
:
Working paper
›
Preprint
File
Knowledge Base
100%
Large Language Model
100%
Learning Context
25%
Intensive Task
12%
Natural Language Processing
12%
Evaluating the adversarial robustness of retrieval-based in-context learning for large kanguage models
Yu, S. C. L., He, J.,
Minervini, P.
&
Pan, J. Z.
,
24 May 2024
,
ArXiv
.
Research output
:
Working paper
›
Preprint
File
Adversarial Machine Learning
100%
Information Retrieval
100%
Large Language Model
66%
Generative Pre-Trained Transformer 3
33%
COTET: Cross-view optimal transport for knowledge graph entity typing
Hu, Z., Gutiérrez-Basulto, V., Xiang, Z., Li, R. &
Pan, J. Z.
,
22 May 2024
,
ArXiv
.
Research output
:
Working paper
›
Preprint
File
Knowledge Graph
100%
Granularity
14%
Contextual Information
14%
False Negative
14%
Entity Cluster
14%
Leveraging intra-modal and inter-modal interaction for multi-modal entity alignment
Hu, Z., Gutiérrez-Basulto, V., Xiang, Z., Li, R. &
Pan, J. Z.
,
19 Apr 2024
,
ArXiv
,
p. 1-10
,
10 p.
Research output
:
Working paper
›
Preprint
File