Giovanni Monea
4 papers · 2024–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
π
Conference Polyglot Β· Bronze
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(10)
π£
Hot Topic Early Bird
β
The Questioner
(2)
Top co-authors
Research topics
Keywords
large language model
(2)
transformer model
(2)
representation learning
(2)
retrieval-augmented generation
(2)
multilingual language model
(2)
prior knowledge
(1)
latent representation
(1)
mechanistic interpretability
(1)
model internal
(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)
context sensitivity
(1)
activation patching
(1)
Papers
Controllable Context Sensitivity and the Knob Behind It
ICLR 2025
Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
ACL 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