Naoya Inoue

104 papers A* 7A 1B 9C 4Misc 1Journal 49Unranked 33
YearRankTypeTitle / Venue / Authors
2026 J jnl
Beyond Forgetting: Machine Unlearning Elicits Controllable Side Behaviors and Capabilities.
CoRR
Tien Dang, The-Hai Nguyen, Dinh Mai Phuong, Nguyen Minh Phuong, Hoang Thanh-Tung, Le-Minh Nguyen, Naoya Inoue
2026 — conf
Improving Chain-of-Thought for Logical Reasoning via Attention-Aware Intervention.
EACL (Findings)
Phuong Minh Nguyen, Dang Huu-Tien, Naoya Inoue
2026 J jnl
Improving Chain-of-Thought for Logical Reasoning via Attention-Aware Intervention.
CoRR
Nguyen Minh Phuong, Tien Huu Dang, Naoya Inoue
2026 J jnl
Improving LLM Unlearning Robustness via Random Perturbations.
Trans. Mach. Learn. Res.
Dang Huu-Tien, Hoang Thanh-Tung, Anh Tuan Bui, Nguyen Minh Phuong, Nguyen Minh Le, Naoya Inoue
2026 — conf
On the Additive Compositionality of Task Vectors in Vision-Language Models.
EACL (Volume 2: Short Papers)
Yuting Shi, Houjing Wei, Naoya Inoue
2025 J jnl
Affinity and Diversity: A Unified Metric for Demonstration Selection via Internal Representations.
CoRR
Mariko Kato, Hakaze Cho, Yoshihiro Sakai, Naoya Inoue
2025 J jnl
Binary Autoencoder for Mechanistic Interpretability of Large Language Models.
CoRR
Hakaze Cho, Haolin Yang, Brian M. Kurkoski, Naoya Inoue
2025 — conf
CyLLM-DAP: Cybersecurity Domain-Adaptive Pre-Training Framework of Large Language Models.
ICISSP (2)
Khang Mai, Razvan Beuran, Naoya Inoue
2025 J jnl
Detecting and Rectifying Noisy Labels: A Similarity-based Approach.
CoRR
Dang Huu-Tien, Naoya Inoue
2025 — conf
FOCUS: A Benchmark for Targeted Socratic Question Generation via Source-Span Grounding.
IJCNLP-AACL (long papers)
Surawat Pothong, Machi Shimmei, Naoya Inoue, Paul Reisert, Ana Brassard, Wenzhi Wang, Shoichi Naito, Jungmin Choi, Kentaro Inui
2025 — conf
Fine-grained Confidence Estimation for Spurious Correctness Detection in Large Language Models.
IJCNLP-AACL (long papers)
Ai Ishii, Naoya Inoue, Hisami Suzuki, Satoshi Sekine
2025 A* conf
Identification of Multiple Logical Interpretations in Counter-Arguments.
EMNLP
Wenzhi Wang, Paul Reisert, Shoichi Naito, Naoya Inoue, Machi Shimmei, Surawat Pothong, Jungmin Choi, Kentaro Inui
2025 — conf
Improve Smart Contract Vulnerability Explanation with Synthetic Data and Chain-of-Thought Prompting.
NLDB (1)
Nguyen Le Minh, Naoya Inoue, Le-Minh Nguyen
2025 J jnl
Improving the Robustness of Representation Misdirection for Large Language Model Unlearning.
CoRR
Huu-Tien Dang, Hoang Thanh-Tung, Le-Minh Nguyen, Naoya Inoue
2025 — conf
LLM DEBATE OPPONENT : Counter-argument Generation focusing on Implicit and Critical Premises.
NAACL (Student Research Workshop)
Taisei Ozaki, Chihiro Nakagawa, Naoya Inoue, Shoichi Naito, Kenshi Yamaguchi
2025 J jnl
Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis.
CoRR
Haolin Yang, Hakaze Cho, Naoya Inoue
2025 J jnl
Mechanism of Task-oriented Information Removal in In-context Learning.
CoRR
Hakaze Cho, Haolin Yang, Gouki Minegishi, Naoya Inoue
2025 J jnl
Mechanistic Fine-tuning for In-context Learning.
CoRR
Hakaze Cho, Peng Luo, Mariko Kato, Rin Kaenbyou, Naoya Inoue
2025 J jnl
Non-Iterative Symbolic-Aided Chain-of-Thought for Logical Reasoning.
CoRR
Phuong Minh Nguyen, Tien Huu Dang, Naoya Inoue
2025 A* conf
On Effects of Steering Latent Representation for Large Language Model Unlearning.
AAAI
Huu-Tien Dang, Tin Pham, Hoang Thanh-Tung, Naoya Inoue
2025 A* conf
Revisiting In-context Learning Inference Circuit in Large Language Models.
ICLR
Hakaze Cho, Mariko Kato, Yoshihiro Sakai, Naoya Inoue
2025 J jnl
StaICC: Standardized Evaluation for Classification Task in In-context Learning.
CoRR
Hakaze Cho, Naoya Inoue
2025 J jnl
Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight.
CoRR
Haolin Yang, Hakaze Cho, Kaize Ding, Naoya Inoue
2025 J jnl
The 30th Anniversary Initiatives of the Association for Natural Language Processing.
J. Nat. Lang. Process.
Naoya Inoue, Hiroki Ouchi, Daisuke Kawahara, Sadao Kurohashi, Mamoru Komachi, Katsuhito Sudoh, Ryo Nagata, Shigeki Matsubara, Yusuke Miyao
2025 A* conf
The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs.
EMNLP
Hinata Tezuka, Naoya Inoue
2025 J jnl
The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs.
CoRR
Hinata Tezuka, Naoya Inoue
2025 — conf
Token-based Decision Criteria Are Suboptimal in In-context Learning.
NAACL (Long Papers)
Hakaze Cho, Yoshihiro Sakai, Mariko Kato, Kenshiro Tanaka, Akira Ishii, Naoya Inoue
2025 J jnl
Token-based Decision Criteria Are Suboptimalin In-context Learning.
J. Nat. Lang. Process.
Hakaze Cho, Naoya Inoue
2025 B conf
Understanding Token Probability Encoding in Output Embeddings.
COLING
Hakaze Cho, Yoshihiro Sakai, Kenshiro Tanaka, Mariko Kato, Naoya Inoue
2025 J jnl
Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning.
CoRR
Haolin Yang, Hakaze Cho, Yiqiao Zhong, Naoya Inoue
2024 C conf
A Viewpoints Embedded Diff-table System For Cross-sectional Insight Survey In a Research Task.
PACLIC
Jinghong Li, Naoya Inoue, Shinobu Hasegawa
2024 — conf
Arukikata Travelogue Dataset with Geographic Entity Mention, Coreference, and Link Annotation.
EACL (Findings)
Shohei Higashiyama, Hiroki Ouchi, Hiroki Teranishi, Hiroyuki Otomo, Yusuke Ide, Aitaro Yamamoto, Hiroyuki Shindo, Yuki Matsuda, Shoko Wakamiya, Naoya Inoue, Ikuya Yamada, Taro Watanabe
2024 — conf
Designing Logic Pattern Templates for Counter-Argument Logical Structure Analysis.
EMNLP (Findings)
Shoichi Naito, Wenzhi Wang, Paul Reisert, Naoya Inoue, Camélia Guerraoui, Kenshi Yamaguchi, Jungmin Choi, Irfan Robbani, Surawat Pothong, Kentaro Inui
2024 — conf
Find-the-Common: A Benchmark for Explaining Visual Patterns from Images.
LREC/COLING
Yuting Shi, Naoya Inoue, Houjing Wei, Yufeng Zhao, Tao Jin
2024 A* conf
Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling.
EMNLP
Irfan Robbani, Paul Reisert, Surawat Pothong, Naoya Inoue, Camélia Guerraoui, Wenzhi Wang, Shoichi Naito, Jungmin Choi, Kentaro Inui
2024 J jnl
Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling.
CoRR
Irfan Robbani, Paul Reisert, Naoya Inoue, Surawat Pothong, Camélia Guerraoui, Wenzhi Wang, Shoichi Naito, Jungmin Choi, Kentaro Inui
2024 — conf
JEMHopQA: Dataset for Japanese Explainable Multi-Hop Question Answering.
LREC/COLING
Ai Ishii, Naoya Inoue, Hisami Suzuki, Satoshi Sekine
2024 J jnl
NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning.
CoRR
Yufeng Zhao, Yoshihiro Sakai, Naoya Inoue
2024 J jnl
On Effects of Steering Latent Representation for Large Language Model Unlearning.
CoRR
Huu-Tien Dang, Trung-Tin Pham, Hoang Thanh-Tung, Naoya Inoue
2024 J jnl
Phase Diagram of Vision Large Language Models Inference: A Perspective from Interaction across Image and Instruction.
CoRR
Houjing Wei, Hakaze Cho, Yuting Shi, Naoya Inoue
2024 J jnl
Revisiting In-context Learning Inference Circuit in Large Language Models.
CoRR
Hakaze Cho, Mariko Kato, Yoshihiro Sakai, Naoya Inoue
2024 J jnl
Token-based Decision Criteria Are Suboptimal in In-context Learning.
CoRR
Hakaze Cho, Yoshihiro Sakai, Mariko Kato, Kenshiro Tanaka, Akira Ishii, Naoya Inoue
2024 J jnl
Understanding Token Probability Encoding in Output Embeddings.
CoRR
Hakaze Cho, Yoshihiro Sakai, Kenshiro Tanaka, Mariko Kato, Naoya Inoue
2023 J jnl
Arukikata Travelogue Dataset with Geographic Entity Mention, Coreference, and Link Annotation.
CoRR
Shohei Higashiyama, Hiroki Ouchi, Hiroki Teranishi, Hiroyuki Otomo, Yusuke Ide, Aitaro Yamamoto, Hiroyuki Shindo, Yuki Matsuda, Shoko Wakamiya, Naoya Inoue, Ikuya Yamada, Taro Watanabe
2023 J jnl
Arukikata Travelogue Dataset.
CoRR
Hiroki Ouchi, Hiroyuki Shindo, Shoko Wakamiya, Yuki Matsuda, Naoya Inoue, Shohei Higashiyama, Satoshi Nakamura, Taro Watanabe
2023 C conf
Counterfactual Adversarial Training for Improving Robustness of Pre-trained Language Models.
PACLIC
Hoai Linh Luu, Naoya Inoue
2023 — conf
Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach.
EMNLP (Findings)
Daichi Haraguchi, Kiyoaki Shirai, Naoya Inoue, Natthawut Kertkeidkachorn
2023 J jnl
Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach.
CoRR
Daichi Haraguchi, Kiyoaki Shirai, Naoya Inoue, Natthawut Kertkeidkachorn
2023 — conf
Teach Me How to Argue: A Survey on NLP Feedback Systems in Argumentation.
ArgMining@EMNLP
Camélia Guerraoui, Paul Reisert, Naoya Inoue, Farjana Sultana Mim, Keshav Singh, Jungmin Choi, Irfan Robbani, Shoichi Naito, Wenzhi Wang, Kentaro Inui
2023 J jnl
Teach Me How to Improve My Argumentation Skills: A Survey on Feedback in Argumentation.
CoRR
Camélia Guerraoui, Paul Reisert, Naoya Inoue, Farjana Sultana Mim, Shoichi Naito, Jungmin Choi, Irfan Robbani, Wenzhi Wang, Kentaro Inui
2022 B conf
IRAC: A Domain-Specific Annotated Corpus of Implicit Reasoning in Arguments.
LREC
Keshav Singh, Naoya Inoue, Farjana Sultana Mim, Shoichi Naitoh, Kentaro Inui
2022 B conf
LPAttack: A Feasible Annotation Scheme for Capturing Logic Pattern of Attacks in Arguments.
LREC
Farjana Sultana Mim, Naoya Inoue, Shoichi Naito, Keshav Singh, Kentaro Inui
2022 J jnl
LPAttack: A Feasible Annotation Scheme for Capturing Logic Pattern of Attacks in Arguments.
CoRR
Farjana Sultana Mim, Naoya Inoue, Shoichi Naito, Keshav Singh, Kentaro Inui
2022 — conf
Learning and Evaluating Character Representations in Novels.
ACL (Findings)
Naoya Inoue, Charuta Pethe, Allen Kim, Steven Skiena
2022 B conf
TYPIC: A Corpus of Template-Based Diagnostic Comments on Argumentation.
LREC
Shoichi Naito, Shintaro Sawada, Chihiro Nakagawa, Naoya Inoue, Kenshi Yamaguchi, Iori Shimizu, Farjana Sultana Mim, Keshav Singh, Kentaro Inui
2022 J jnl
TYPIC: A Corpus of Template-Based Diagnostic Comments on Argumentation.
CoRR
Shoichi Naito, Shintaro Sawada, Chihiro Nakagawa, Naoya Inoue, Kenshi Yamaguchi, Iori Shimizu, Farjana Sultana Mim, Keshav Singh, Kentaro Inui
2021 J jnl
A Comparative Study on Collecting High-Quality Implicit Reasonings at a Large-scale.
CoRR
Keshav Singh, Paul Reisert, Naoya Inoue, Kentaro Inui
2021 J jnl
Annotating Implicit Reasoning in Arguments with Causal Links.
CoRR
Keshav Singh, Naoya Inoue, Farjana Sultana Mim, Shoichi Naitoh, Kentaro Inui
2021 — conf
Cleaning Dirty Books: Post-OCR Processing for Previously Scanned Texts.
EMNLP (Findings)
Allen Kim, Charuta Pethe, Naoya Inoue, Steven Skiena
2021 J jnl
Cleaning Dirty Books: Post-OCR Processing for Previously Scanned Texts.
CoRR
Allen Kim, Charuta Pethe, Naoya Inoue, Steven Skiena
2021 J jnl
Corruption Is Not All Bad: Incorporating Discourse Structure Into Pre-Training via Corruption for Essay Scoring.
IEEE ACM Trans. Audio Speech Lang. Process.
Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi, Kentaro Inui
2021 — conf
Exploring Methodologies for Collecting High-Quality Implicit Reasoning in Arguments.
ArgMining@EMNLP
Keshav Singh, Farjana Sultana Mim, Naoya Inoue, Shoichi Naito, Kentaro Inui
2021 — conf
Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension.
EMNLP (1)
Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui
2021 J jnl
Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension.
CoRR
Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui
2021 A conf
Two Training Strategies for Improving Relation Extraction over Universal Graph.
EACL
Qin Dai, Naoya Inoue, Ryo Takahashi, Kentaro Inui
2021 J jnl
Two Training Strategies for Improving Relation Extraction over Universal Graph.
CoRR
Qin Dai, Naoya Inoue, Ryo Takahashi, Kentaro Inui
2020 J jnl
Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring.
CoRR
Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi, Kentaro Inui
2020 B conf
Modeling Event Salience in Narratives via Barthes' Cardinal Functions.
COLING
Takaki Otake, Sho Yokoi, Naoya Inoue, Ryo Takahashi, Tatsuki Kuribayashi, Kentaro Inui
2020 J jnl
Modeling Event Salience in Narratives via Barthes' Cardinal Functions.
CoRR
Takaki Otake, Sho Yokoi, Naoya Inoue, Ryo Takahashi, Tatsuki Kuribayashi, Kentaro Inui
2020 A* conf
R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason.
ACL
Naoya Inoue, Pontus Stenetorp, Kentaro Inui
2019 — conf
An Annotation Protocol for Collecting User-Generated Counter-Arguments Using Crowdsourcing.
AIED (2)
Paul Reisert, Gisela Vallejo, Naoya Inoue, Iryna Gurevych, Kentaro Inui
2019 — conf
An Empirical Study of Span Representations in Argumentation Structure Parsing.
ACL (1)
Tatsuki Kuribayashi, Hiroki Ouchi, Naoya Inoue, Paul Reisert, Toshinori Miyoshi, Jun Suzuki, Kentaro Inui
2019 — conf
Inject Rubrics into Short Answer Grading System.
DeepLo@EMNLP-IJCNLP
Tianqi Wang, Naoya Inoue, Hiroki Ouchi, Tomoya Mizumoto, Kentaro Inui
2019 J jnl
RC-QED: Evaluating Natural Language Derivations in Multi-Hop Reading Comprehension.
CoRR
Naoya Inoue, Pontus Stenetorp, Kentaro Inui
2019 J jnl
Riposte! A Large Corpus of Counter-Arguments.
CoRR
Paul Reisert, Benjamin Heinzerling, Naoya Inoue, Shun Kiyono, Kentaro Inui
2019 J jnl
Survey on frontiers of language and robotics.
Adv. Robotics
Tadahiro Taniguchi, Daichi Mochihashi, Takayuki Nagai, Satoru Uchida, Naoya Inoue, Ichiro Kobayashi, Tomoaki Nakamura, Yoshinobu Hagiwara, Naoto Iwahashi, Tetsunari Inamura
2019 — conf
Unsupervised Learning of Discourse-Aware Text Representation for Essay Scoring.
ACL (2)
Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi, Kentaro Inui
2019 J jnl
When Choosing Plausible Alternatives, Clever Hans can be Clever.
CoRR
Pride Kavumba, Naoya Inoue, Benjamin Heinzerling, Keshav Singh, Paul Reisert, Kentaro Inui
2018 — conf
Feasible Annotation Scheme for Capturing Policy Argument Reasoning using Argument Templates.
ArgMining@EMNLP
Paul Reisert, Naoya Inoue, Tatsuki Kuribayashi, Kentaro Inui
2018 C conf
Improving Scientific Relation Classification with Task Specific Supersense.
PACLIC
Qin Dai, Naoya Inoue, Paul Reisert, Kentaro Inui
2018 J jnl
Leveraging Unannotated Texts for Scientific Relation Extraction.
IEICE Trans. Inf. Syst.
Qin Dai, Naoya Inoue, Paul Reisert, Kentaro Inui
2017 J jnl
A Corpus of Deep Argumentative Structures as an Explanation to Argumentative Relations.
CoRR
Paul Reisert, Naoya Inoue, Naoaki Okazaki, Kentaro Inui
2017 Misc conf
A Scalable Weighted Max-SAT Implementation of Propositional Etcetera Abduction.
FLAIRS
Naoya Inoue, Andrew S. Gordon
2017 — conf
An RNN-based Binary Classifier for the Story Cloze Test.
LSDSem@EACL
Melissa Roemmele, Sosuke Kobayashi, Naoya Inoue, Andrew Gordon
2017 — conf
Generating Stylistically Consistent Dialog Responses with Transfer Learning.
IJCNLP(2)
Reina Akama, Kazuaki Inada, Naoya Inoue, Sosuke Kobayashi, Kentaro Inui
2017 — conf
Handling Multiword Expressions in Causality Estimation.
IWCS(2)
Shota Sasaki, Sho Takase, Naoya Inoue, Naoaki Okazaki, Kentaro Inui
2017 — conf
Leveraging Document-Specific Information for Classifying Relations in Scientific Articles.
JSAI-isAI Workshops
Qin Dai, Naoya Inoue, Paul Reisert, Kentaro Inui
2016 B conf
Modeling Context-sensitive Selectional Preference with Distributed Representations.
COLING
Naoya Inoue, Yuichiroh Matsubayashi, Masayuki Ono, Naoaki Okazaki, Kentaro Inui
2015 — conf
A Computational Approach for Generating Toulmin Model Argumentation.
ArgMining@HLT-NAACL
Paul Reisert, Naoya Inoue, Naoaki Okazaki, Kentaro Inui
2014 C conf
An Example-Based Approach to Difficult Pronoun Resolution.
PACLIC
Canasai Kruengkrai, Naoya Inoue, Jun Sugiura, Kentaro Inui
2014 J jnl
Background Estimation for a Single Omnidirectional Image Sequence Captured with a Moving Camera.
Inf. Media Technol.
Norihiko Kawai, Naoya Inoue, Tomokazu Sato, Fumio Okura, Yuta Nakashima, Naokazu Yokoya
2014 J jnl
Background Estimation for a Single Omnidirectional Image Sequence Captured with a Moving Camera.
IPSJ Trans. Comput. Vis. Appl.
Norihiko Kawai, Naoya Inoue, Tomokazu Sato, Fumio Okura, Yuta Nakashima, Naokazu Yokoya
2014 J jnl
ILP-based Inference for Cost-based Abduction on First-order Predicate Logic.
Inf. Media Technol.
Naoya Inoue, Kentaro Inui
2013 — conf
Discriminative Learning of First-Order Weighted Abduction from Partial Discourse Explanations.
CICLing (1)
Kazeto Yamamoto, Naoya Inoue, Yotaro Watanabe, Naoaki Okazaki, Kentaro Inui
2013 — conf
Recognizing Implicit Discourse Relations through Abductive Reasoning with Large-scale Lexical Knowledge.
NLPAR@LPNMR
Jun Sugiura, Naoya Inoue, Kentaro Inui
2012 B conf
Coreference Resolution with ILP-based Weighted Abduction.
COLING
Naoya Inoue, Ekaterina Ovchinnikova, Kentaro Inui, Jerry R. Hobbs
2012 B conf
Large-Scale Cost-Based Abduction in Full-Fledged First-Order Predicate Logic with Cutting Plane Inference.
JELIA
Naoya Inoue, Kentaro Inui
2012 — conf
Simultaneous Learning of Localized Multiple Kernels and Classifier with Weighted Regularization.
SSPR/SPR
Naoya Inoue, Yukihiko Yamashita
2011 — conf
ILP-Based Reasoning for Weighted Abduction.
Plan, Activity, and Intent Recognition
Naoya Inoue, Kentaro Inui
2011 A* conf
Selective injection and laser manipulation of nanotool inside a specific cell using Optical pH regulation and optical tweezers.
ICRA
Hisataka Maruyama, Naoya Inoue, Taisuke Masuda, Fumihito Arai
2010 J jnl
Geometrically local isotropic independence and numerical analysis of the Mahalanobis metric in vector space.
Pattern Recognit. Lett.
Joken Son, Naoya Inoue, Yukihiko Yamashita
2010 J jnl
Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases.
Inf. Media Technol.
Naoya Inoue, Ryu Iida, Kentaro Inui, Yuji Matsumoto
2008 B conf
Numerical analysis of Mahalanobis metric in vector space.
ICPR
Joken Son, Naoya Inoue, Yukihiko Yamashita
2006 — conf
Maxwell Normal Distribution in a Manifold and Mahalanobis Metric.
SSPR/SPR
Yukihiko Yamashita, Mariko Numakami, Naoya Inoue