Hosein Mohebbi
9 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🗺️ Taxonomy Completionist (17) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge
🐝
Cross-Pollinator
(12)
🌈
Renaissance Researcher
(5)
🔥
Unstoppable
(5)
❓
The Questioner
Conferences
EMNLP (5)
EACL (2)
ACL (1)
NAACL (1)
Top co-authors
Keywords
probing analysis
(2)
context mixing
(2)
representation learning
(1)
speech recognition
(1)
syntactic analysis
(1)
neural network analysis
(1)
linguistic knowledge
(1)
transformer encoder
(1)
token representation
(1)
model interpretability
(1)
layer-wise analysis
(1)
inference optimization
(1)
mechanistic interpretability
(1)
token pruning
(1)
inference speedup
(1)
efficient computing
(1)
attribution method
(1)
semantic encoding
(1)
knowledge transfer
(1)
transformer architecture
(1)
Papers
Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models
EMNLP 2025
How Language Models Prioritize Contextual Grammatical Cues?
EMNLP 2024
Transformer-specific Interpretability
EACL 2024
DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
NAACL 2024
Quantifying Context Mixing in Transformers
EACL 2023
Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers
EMNLP 2023
AdapLeR: Speeding up Inference by Adaptive Length Reduction
ACL 2022
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations
EMNLP 2021
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results
EMNLP 2021