Jason Hoelscher-Obermaier
4 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (12) π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(13)
π£
Hot Topic Early Bird
Conferences
AAAI (1)
AACL (1)
ACL (1)
EMNLP (1)
Top co-authors
Keywords
benchmark evaluation
(1)
knowledge editing
(1)
kl divergence
(1)
model editing
(1)
ai safety
(1)
knowledge graph
(1)
evaluation metric
(1)
token probability
(1)
emergent capability
(1)
word embedding
(1)
defense mechanism
(1)
specificity benchmark
(1)
large language model
(1)
multi-agent system
(1)
agent compromise
(1)
malicious prompt
(1)
security trade-off
(1)
collaboration capability
(1)
biomedical terminology
(1)
latent semantic imputation
(1)
Papers
Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems
AAAI 2025
Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark
ACL 2023
Self-Consistency of Large Language Models under Ambiguity
EMNLP 2023
Leveraging knowledge graphs to update scientific word embeddings using latent semantic imputation
AACL 2022