Tatsuya Hiraoka
19 papers · 2019–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🏃 Academic Marathon (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (12)
🌍
Conference Polyglot
(6)
🏃
Academic Marathon
(6)
🏆
Keyword Champion
(4)
🗃️
Keyword Collector
(65)
⚡
Prolific Year
(8)
💎
Century Club
(17)
❓
The Questioner
Conferences
ACL (7)
EMNLP (3)
NAACL (3)
COLING (2)
IJCNLP (2)
AACL (1)
EACL (1)
Top co-authors
Keywords
text classification
(6)
language model
(4)
subword regularization
(4)
repetition neuron
(3)
attention head
(3)
in-context learning
(3)
machine translation
(2)
skill neuron
(2)
induction head
(2)
mechanistic interpretability
(2)
sentiment analysis
(2)
named entity recognition
(2)
neural machine translation
(2)
subword tokenization
(2)
large language model
(2)
convolutional neural network
(1)
hidden markov model
(1)
neural network activation
(1)
joint learning
(1)
relation extraction
(1)
Papers
Sycophancy Hides Linearly in the Attention Heads
EACL 2026
Corpus-Dependent Subcharacter Encoding via HMM-Guided Code Assignment
ACL 2026
Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning
AACL 2025
Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
ACL 2025
SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization
COLING 2025
Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors
EMNLP 2025
Spelling-out is not Straightforward: LLMs’ Capability of Tokenization from Token to Characters
EMNLP 2025
Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning
IJCNLP 2025
Repetition Neurons: How Do Language Models Produce Repetitions?
NAACL 2025
The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces
NAACL 2025
An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
NAACL 2024
Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation
ACL 2022
Word-level Perturbation Considering Word Length and Compositional Subwords
ACL 2022
Joint Entity and Relation Extraction Based on Table Labeling Using Convolutional Neural Networks
ACL 2022
MaxMatch-Dropout: Subword Regularization for WordPiece
COLING 2022
Joint Optimization of Tokenization and Downstream Model
IJCNLP 2021
Joint Optimization of Tokenization and Downstream Model
ACL 2021
Optimizing Word Segmentation for Downstream Task
EMNLP 2020
Stochastic Tokenization with a Language Model for Neural Text Classification
ACL 2019