Javier Ferrando
14 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (4) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (26) π£ Hot Topic Early Bird
π£
Hot Topic Early Bird
π
Keyword Champion
(2)
π¬
Deep Specialist
(10)
ποΈ
Keyword Collector
(57)
π
Century Club
(14)
π₯
Unstoppable
(5)
β
The Questioner
Conferences
EMNLP (8)
ACL (4)
AAAI (1)
ICLR (1)
Top co-authors
Keywords
neural machine translation
(5)
attention mechanism
(5)
transformer model
(3)
attention head
(3)
model interpretability
(2)
machine translation
(2)
residual stream
(2)
mechanistic interpretability
(2)
circuit analysis
(2)
large language model
(2)
evaluation framework
(1)
efficient computing
(1)
feature attribution
(1)
multilingual nlp
(1)
self-attention mechanism
(1)
model behavior
(1)
context understanding
(1)
pre-trained model
(1)
language model
(1)
toxicity detection
(1)
Papers
Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
ICLR 2025
LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models
ACL 2024
Information Flow Routes: Automatically Interpreting Language Models at Scale
EMNLP 2024
Neurons in Large Language Models: Dead, N-gram, Positional
ACL 2024
On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task
EMNLP 2024
Automating Behavioral Testing in Machine Translation
EMNLP 2023
Toxicity in Multilingual Machine Translation at Scale
EMNLP 2023
Explaining How Transformers Use Context to Build Predictions
ACL 2023
Measuring the Mixing of Contextual Information in the Transformer
EMNLP 2022
On the Locality of Attention in Direct Speech Translation
ACL 2022
Interpreting Gender Bias in Neural Machine Translation: Multilingual Architecture Matters
AAAI 2022
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer
EMNLP 2022
The TALP-UPC Participation in WMT21 News Translation Task: an mBART-based NMT Approach
EMNLP 2021
Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions
EMNLP 2021