KI
Kentaro Inui
cs.CLcs.LGcs.AIcs.CVstat.MLAutism Spectrum Disordercmp-lgCommunicationcs.CYcs.HC
On Valency
published · living versionsW_4q6dzwp2·v1 · currentpublished
Why Do LLMs Accept Generics? Explaining Acceptability using Psycholinguistic and Model-Derived Factors
with Mervat Abassy, Zhaoxin Feng, Tatsuki Kuribayashi, Emmanuele Chersoni
1 version
W_684rvgfj·v1published
W_bz7hpxvc·v1published
Preprints & journals
128 papers in the corpus · 1997–2026Why Do LLMs Accept Generics? Explaining Acceptability using Psycholinguistic and Model-Derived Factors2610.27928v1 · Mervat Abassy, Zhaoxin Feng, Tatsuki Kuribayashi et al.2026 · 0 citationsarXivon Valency
When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction2610.28393v1 · Jinghui Zhang, Lang Gao, Zongfang Liu et al.2026 · 0 citationsarXivon Valency
Rethinking Contextualization by Reinterpreting Attention Head Channels2609.33851v1 · Hakaze Cho, Haolin Yang, Zhun Sun et al.2026 · 0 citationsarXiv
How Well Does AI-Generated Feedback Work? Intrinsic and Extrinsic Evaluation across more than 20,000 EFL Essay Drafts2607.14591v1 · Steven Coyne, Diana Galvan-Sosa, Ryan Spring et al.2026 · 0 citationsAIED CCIS 3031 (2026) 247-253
Sycophancy Hides Linearly in the Attention Heads2601.16644v1 · Rifo Genadi, Munachiso Nwadike, Nurdaulet Mukhituly et al.2026 · 0 citationsarXiv
Correction: Toward mapping pragmatic impairment of autism spectrum disorder individuals through the development of a corpus of spoken Japanese.41021439 · Kato, Sumi, Hanawa, Kazuaki, Linh, Vo Phuong et al.2025 · 0 citationsPloS one. 2025;20(9):e0333589
Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki2509.04432v3 · Mutsumi Sasaki, Go Kamoda, Ryosuke Takahashi et al.2025 · 0 citationsarXiv
Uncovering the Spectral Bias in Diagonal State Space Models2508.20441v1 · Ruben Solozabal, Velibor Bojkovic, Hilal AlQuabeh et al.2025 · 0 citationsarXiv
Annotating Errors in English Learners' Written Language Production: Advancing Automated Written Feedback Systems2508.06810v1 · Steven Coyne, Diana Galvan-Sosa, Ryan Spring et al.2025 · 1 citationAIED LNCS 15880 (2025) 292-306
Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning2507.07810v2 · Nhi Hoai Doan, Tatsuya Hiraoka, Kentaro Inui2025 · 0 citationsarXiv
TopK Language Models2506.21468v1 · Ryosuke Takahashi, Tatsuro Inaba, Kentaro Inui et al.2025 · 0 citationsarXiv
Emergence of Primacy and Recency Effect in Mamba: A Mechanistic Point of View2506.15156v1 · Muhammad Cendekia Airlangga, Hilal AlQuabeh, Munachiso S Nwadike et al.2025 · 0 citationsarXiv
Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters2506.10641v1 · Tatsuya Hiraoka, Kentaro Inui2025 · 1 citationarXiv
LLMs Can Compensate for Deficiencies in Visual Representations2506.05439v2 · Sho Takishita, Jay Gala, Abdelrahman Mohamed et al.2025 · 0 citationsarXiv
On Entity Identification in Language Models2506.02701v4 · Masaki Sakata, Benjamin Heinzerling, Sho Yokoi et al.2025 · 0 citationsarXiv
Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance2505.21458v1 · Shintaro Ozaki, Tatsuya Hiraoka, Hiroto Otake et al.2025 · 0 citationsarXiv
Mechanistic Insights into Grokking from the Embedding Layer2505.15624v1 · H.V.AlquBoj, Hilal AlQuabeh, Velibor Bojkovic et al.2025 · 0 citationsarXiv
SPIRIT: Patching Speech Language Models against Jailbreak Attacks2505.13541v2 · Amirbek Djanibekov, Nurdaulet Mukhituly, Kentaro Inui et al.2025 · 3 citationsarXiv
Tell Me Who Your Students Are: GPT Can Generate Valid Multiple-Choice Questions When Students' (Mis)Understanding Is Hinted2505.05815v2 · Machi Shimmei, Masaki Uto, Yuichiroh Matsubayashi et al.2025 · 0 citationsarXiv
SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation2505.00831v6 · Quang P. M. Pham, Khoi T. N. Nguyen, Nhi H. Doan et al.2025 · 0 citationsarXiv
How Individual Traits and Language Styles Shape Preferences In Open-ended User-LLM Interaction: A Preliminary Study2504.17083v1 · Rendi Chevi, Kentaro Inui, Thamar Solorio et al.2025 · 1 citationarXiv
Correction: Toward mapping pragmatic impairment of autism spectrum disorder individuals through the development of a corpus of spoken Japanese.40168413 · Kato, Sumi, Hanawa, Kazuaki, Nguyen, Vo Phuong Linh et al.2025 · 0 citationsPloS one. 2025;20(4):e0321852
How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders2503.06394v2 · Tatsuro Inaba, Go Kamoda, Kentaro Inui et al.2025 · 1 citationarXiv
Syntactic Learnability of Echo State Neural Language Models at Scale2503.01724v1 · Ryo Ueda, Tatsuki Kuribayashi, Shunsuke Kando et al.2025 · 0 citationsarXiv
Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning2502.20620v2 · Ayana Niwa, Masahiro Kaneko, Kentaro Inui2025 · 2 citationsarXiv
Number Representations in LLMs: A Computational Parallel to Human Perception2502.16147v1 · H.V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic et al.2025 · 0 citationsarXiv
Large Language Models Are Human-Like Internally2502.01615v2 · Tatsuki Kuribayashi, Yohei Oseki, Souhaib Ben Taieb et al.2025 · 10 citationsarXiv
FinchGPT: a Transformer based language model for birdsong analysis2502.00344v1 · Kosei Kobayashi, Kosuke Matsuzaki, Masaya Taniguchi et al.2025 · 1 citationarXiv
Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference2501.15754v3 · Go Kamoda, Benjamin Heinzerling, Tatsuro Inaba et al.2025 · 0 citationsarXiv
Automatic Feedback Generation for Short Answer Questions using Answer Diagnostic Graphs2501.15777v1 · Momoka Furuhashi, Hiroaki Funayama, Yuya Iwase et al.2025 · 1 citationarXiv
RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles2501.13491v1 · Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu et al.2025 · 0 citationsarXiv
LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics2412.01113v4 · Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi et al.2024 · 3 citationsarXiv
The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces2410.13194v2 · Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh et al.2024 · 1 citationarXiv
Repetition Neurons: How Do Language Models Produce Repetitions?2410.13497v2 · Tatsuya Hiraoka, Kentaro Inui2024 · 1 citationarXiv
Representational Analysis of Binding in Language Models2409.05448v3 · Qin Dai, Benjamin Heinzerling, Kentaro Inui2024 · 1 citationarXiv
MQM-Chat: Multidimensional Quality Metrics for Chat Translation2408.16390v2 · Yunmeng Li, Jun Suzuki, Makoto Morishita et al.2024 · 0 citationshttps://aclanthology.org/2025.coling-main.221/
An Investigation of Warning Erroneous Chat Translations in Cross-lingual Communication2408.15543v2 · Yunmeng Li, Jun Suzuki, Makoto Morishita et al.2024 · 1 citationIJCNLP-AACL 2023 Student Research Workshop
Reducing the Cost: Cross-Prompt Pre-Finetuning for Short Answer Scoring2408.13966v1 · Hiroaki Funayama, Yuya Asazuma, Yuichiroh Matsubayashi et al.2024 · 13 citationsAIED 2023. Lecture Notes in Computer Science(), vol 13916.pp.78-89. Springer
First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning2406.16078v2 · Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi et al.2024 · 1 citationarXiv
Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling2406.12402v1 · Irfan Robbani, Paul Reisert, Naoya Inoue et al.2024 · 1 citationarXiv
The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models2406.06032v1 · Ryosuke Takahashi, Go Kamoda, Benjamin Heinzerling et al.2024 · 0 citationsarXiv
ACORN: Aspect-wise Commonsense Reasoning Explanation Evaluation2405.04818v2 · Ana Brassard, Benjamin Heinzerling, Keito Kudo et al.2024 · 0 citationsarXiv
A Large Collection of Model-generated Contradictory Responses for Consistency-aware Dialogue Systems2403.12500v1 · Shiki Sato, Reina Akama, Jun Suzuki et al.2024 · 1 citationarXiv
Monotonic Representation of Numeric Properties in Language Models2403.10381v1 · Benjamin Heinzerling, Kentaro Inui2024 · 0 citationsarXiv
Japanese-English Sentence Translation Exercises Dataset for Automatic Grading2403.03396v1 · Naoki Miura, Hiroaki Funayama, Seiya Kikuchi et al.2024 · 0 citationsarXiv
J-UniMorph: Japanese Morphological Annotation through the Universal Feature Schema2402.14411v1 · Kosuke Matsuzaki, Masaya Taniguchi, Kentaro Inui et al.2024 · 0 citationsarXiv
Test-time Augmentation for Factual Probing2310.17121v1 · Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi et al.2023 · 0 citationsarXiv
Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words2310.15921v1 · Hiroto Kurita, Goro Kobayashi, Sho Yokoi et al.2023 · 0 citationsarXiv
Chat Translation Error Detection for Assisting Cross-lingual Communications2308.01044v1 · Yunmeng Li, Jun Suzuki, Makoto Morishita et al.2023 · 4 citationsProceedings of the 3rd Workshop on Evaluation and Comparison of NLP Systems, pages 88-95, November 2022, Online. Association for Computational Linguistics
Teach Me How to Improve My Argumentation Skills: A Survey on Feedback in Argumentation2307.15341v1 · Cam'elia Guerraoui, Paul Reisert, Naoya Inoue et al.2023 · 0 citationsarXiv
Career total: 436 works. 128 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.