Masaru Isonuma
15 papers · 2017–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Academic Marathon (8) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (13)
πΊοΈ
Taxonomy Completionist
(41)
π
Interdisciplinary Bridge
β‘
Prolific Year
(5)
β
The Questioner
ποΈ
Keyword Collector
(71)
π
Century Club
(14)
π
Trend Setter
Conferences
ACL (7)
EMNLP (4)
ICLR (2)
AACL (1)
IJCNLP (1)
Top co-authors
Keywords
large language model
(4)
feature attribution
(2)
abstractive summarization
(2)
variational inference
(2)
continual learning
(2)
instruction tuning
(2)
citation analysis
(2)
topic modeling
(1)
prompt engineering
(1)
model selection
(1)
cross-lingual transfer
(1)
extractive summarization
(1)
self-supervised learning
(1)
short text analysis
(1)
self-attention mechanism
(1)
machine unlearning
(1)
model behavior
(1)
curriculum learning
(1)
text representation
(1)
text summarization
(1)
Papers
Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models
IJCNLP 2025
Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models
AACL 2025
How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders
EMNLP 2025
Instability in Downstream Task Performance During LLM Pretraining
EMNLP 2025
What's New in My Data? Novelty Exploration via Contrastive Generation
ICLR 2025
UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
ICLR 2025
Topic Modeling for Short Texts with Large Language Models
ACL 2024
Unlearning Traces the Influential Training Data of Language Models
ACL 2024
Dynamic Structured Neural Topic Model with Self-Attention Mechanism
ACL 2023
SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation
ACL 2023
Differentiable Instruction Optimization for Cross-Task Generalization
ACL 2023
Lexical Entailment with Hierarchy Representations by Deep Metric Learning
EMNLP 2022
Tree-Structured Neural Topic Model
ACL 2020
Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking
ACL 2019
Extractive Summarization Using Multi-Task Learning with Document Classification
EMNLP 2017