Antonio Serino
3 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(2)
🐝
Cross-Pollinator
(12)
🗺️
Taxonomy Completionist
(13)
Conferences
EACL (1)
EMNLP (1)
IJCAI (1)
Top co-authors
Keywords
large language model
(3)
representation learning
(2)
model evaluation
(1)
semantic analysis
(1)
semantic alignment
(1)
interpretability evaluation
(1)
language model
(1)
feature decomposition
(1)
sparse autoencoder
(1)
ai exposure assessment
(1)
task replacement
(1)
labor market impact
(1)
skill automation
(1)
workforce augmentation
(1)
safety classification
(1)
activation space
(1)
occupational analysis
(1)
polysemantic activation
(1)
feature evaluation
(1)
job exposure
(1)
Papers
Safe-Unsafe Concept Separation Emerges from a Single Direction in Language Models Activation Space
EACL 2026
SFAL: Semantic-Functional Alignment Scores for Distributional Evaluation of Auto-Interpretability in Sparse Autoencoders
EMNLP 2025
Towards the Terminator Economy: Assessing Job Exposure to AI Through LLMs
IJCAI 2025