Giovanni Monea
4 papers · 2024–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (2) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (12) π£ Hot Topic Early Bird
π
Cross-Pollinator
(11)
β
The Questioner
(2)
Conferences
ACL (3)
ICLR (1)
Top co-authors
Keywords
multilingual language model
(2)
large language model
(2)
transformer model
(2)
cross-lingual transfer
(1)
semantic representation
(1)
concept representation
(1)
latent representation
(1)
mechanistic interpretability
(1)
retrieval-augmented generation
(1)
multilingual model
(1)
language bia
(1)
internal representation
(1)
multilingual transformer
(1)
contextual grounding
(1)
factual recall
(1)
causal mediation
(1)
parametric knowledge
(1)
causal tracing
(1)
activation patching
(1)
word translation
(1)
Papers
Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
ACL 2025
Controllable Context Sensitivity and the Knob Behind It
ICLR 2025
A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
ACL 2024
Do Llamas Work in English? On the Latent Language of Multilingual Transformers
ACL 2024