Session Details
[4Yin-A]Poster 6
Thu. Jun 11, 2026 1:00 PM - 2:30 PM JST
Thu. Jun 11, 2026 4:00 AM - 5:30 AM UTC
Thu. Jun 11, 2026 4:00 AM - 5:30 AM UTC
Room Y(Exhibition hall AB 1)
[4Yin-A-01]The Effect of LLM Response Styles on Users' Misinformation Detection Sensitivity
Gakuei SUGIURA1, Yuya TAKADA1, Kira FURUKAWA1, Tatsunosuke YOSHIME1, 〇ZIXIN CUI1 (1. University of Tsukuba)
[4Yin-A-02]Whose Fairness, and for Whom?Value Gaps in AI Ethics and the Conditions for Institutionalization
〇Aoi Miyazaki1 (1. Chiba University)
[4Yin-A-03]Multifaceted Evaluation of Adaptive Fighting Game AI Scaling to Diverse Player Skill Levels
〇KEN YAMANE1, Chao Tang1, Taketo Yoshida1, Keigo Tokuda1, Takumi Kakee1 (1. Teikyo University)
[4Yin-A-04]AI for Anomaly Response Support:Explanation Generation and Action Recommendation via Multimodal RAG
〇Yusuke Yamashina1, Keisuke Niimi1, Caio Cesar Pinheiro de Moura1, Kazuma Shiomi1, Yoshihiko Ichikawa1, Tsukasa Kamo2, Atsushi Kuboya2, Yuji Ayusawa2, Tatsuya Yamamoto2, Keigo Yoshida2 (1. Insight Edge, Inc., 2. SCSK Corporation)
[4Yin-A-05]Toward Explainable Unsupervised Learning: Interpreting Cluster Semantics with Local Large Language Models
〇Caio César Pinheiro de Moura1, Keisuke Niimi1, Yusuke Yamashina1, Kazuma Shiomi1, Yoshihiko Ichikawa1, Tsukasa Kamo2, Atsushi Kuboya2, Yuji Ayusawa2, Tatsuya Yamamoto2, Keigo Yoshida2 (1. Insight Edge, Inc., 2. SCSK Corporation)
[4Yin-A-06]How Many Orders does a Spoofer Need? Investigated by an Agent-Based Model
〇TAKANOBU MIZUTA1, ISAO YAGI2 (1. SPARX Asset Management Co., Ltd., 2. Kogakuin University)
[4Yin-A-07]Construction of a Filter Bubble Detection AI Model Using Multimodal Information
〇Mahiro Nishino1, Kazuyuki Matsumoto2, Minoru Yoshida2 (1. Tokushima University Graduate School of Sciences and Technology for Innovation, 2. Tokushima University Graduate School of Technology, Industrial and Social Sciences)
[4Yin-A-08]Safety-Aligned Vision-Language-Action Models via Plackett-Luce Preference Learning with NLL Regularization
〇Yun Li1, Simon Thompson2, Ehsan Javanmardi1, Alex Orsholits1, Manabu Tsukada1 (1. The University of Tokyo, 2. TIER IV, Inc.)
[4Yin-A-09]A Sales Forecasting Model for New Products Using Clustering and Generative AIAn Evaluation Experiment Using Purchasing Big Data
〇Taichi Fukawa1, Kouta Nakata1, Yusuke Shirota2, Tatsunori Kanai2 (1. Toshiba Corporation, 2. Toshiba Digital Solutions Corporation)
[4Yin-A-10]Multiple Treatment Effect Estimation from Graphical Observational Data
〇Sho Shimazu2,1, Amane Sato2, Soichiro Okazaki1, Atsuki Sawayama2, Fumiya Hori2, Daisuke Okamoto2 (1. The Japan Research Institute, Limited, 2. Sumitomo Mitsui Card Company, Limited)
[4Yin-A-11]Improving Virtue Ethics Judgment by LLM through Fine-tuning and Prompt Optimization with Explanatory Text
〇Kota Hattori1, Toru Sugimoto2 (1. Graduate School of Engineering and Science, Shibaura Institute of Technology, 2. College of Engineering, Shibaura Institute of Technology)
[4Yin-A-12]SAFE: Explaining Group Fairness Metrics via Meta-modeling and SHAP
〇kazuki ohara1 (1. Recruit Co., Ltd.)
[4Yin-A-13]An Analysis of Dementia-Related Stigma in Large Language Models
〇Naoki Hagiyama1, Yoshiaki Takimoto1, Takehi Kurahsima1 (1. NTT)
[4Yin-A-14]Teachers Want AI - But Not That Way― 教師の意識から探る学校AI導入の可能性 ―
〇Tatsuya Tooka1, Yuichiro Wajima1 (1. Hokuriku University)
[4Yin-A-15]Modeling Interdependencies in Online User Behavior via a Multivariate Hawkes Process
〇Shuhei KONDO1 (1. PLAID Inc.)
[4Yin-A-16]Investigation of Reinforcement Learning-Based Personalized Notification Optimization for Habit Formation Support in Mobile Apps
〇Takashi Hasuo1, Shingo Nakazawa1 (1. Theoria technologies Co., Ltd.)
[4Yin-A-17]Rethinking Diversity in News Comment Ranking via Mainstream Separation and Constructive Minority Exposure
〇Zuofan Fang1, Kota Tsubouchi2, Tooru Shimizu2, Nobuhiko Nishio1 (1. Ritsumei University, 2. LY Corporation)
[4Yin-A-18]Token-Level Hallucination Detection Based on Internal Representation Differences in RAG
〇Kazuai Furumai1, Shuichiro Haruta1, Kazunori Matsumoto1, Kazushi Ikeda1 (1. KDDI Research, Inc.)
[4Yin-A-19]Spatial Pricing Strategies of LLM Agents under Heterogeneous Customer Distributions
〇Akio Ikegami1,2, Takehiro Takayanagi1,2, Ryuji Hashimoto1,2, Ryosuke Takata1,2, Kiyoshi Izumi1,2 (1. The University of Tokyo, 2. Simulacra Inc.)
[4Yin-A-20]AI as a Source of Scientific Information: A Cross-National Study of Persuasion and Source Credibility
〇Ruijun Sophia Liu1 (1. University of Tokoy)
[4Yin-A-21]Examining the Mechanism of the Permeation of Corporate Philosophy Using Causal Discovery Methods
〇TAKEO SHIBANO1 (1. HINO Motors, Ltd)
[4Yin-A-22]Correction of Na-adjectives in Japanese Grammatical Error Correction: Effects of Subword Vocabulary Size and Orthography
〇Aomi Yoneda1, Katsuhito Sudoh1 (1. Nara Women's University)
[4Yin-A-23]Development of a large language model with improved causal inference capabilities
〇Hinata Hayashi1, Ichiro Kobayashi1 (1. Ochanomizu University)
[4Yin-A-24]A Study on Optimizing Fragrance Product Images Using AI-generated Backgrounds
〇Masaya Kirishima1, Ryosuke Araki1, Satoshi Shiibashi1 (1. ZOZO, Inc.)
[4Yin-A-25]An AI-Based Golf Swing Evaluation Method Using Pose Estimation
〇Junwei Fan1, Aya Yoshizawa1, Etsuko Ichida1, Kousuke Aoki1 (1. INTEC Inc.)
[4Yin-A-26]Multi-hop Context Refinement: Enhancing RAG via Keyword Extraction and Source-wise Ranking
〇Yuta Tsuchiya1, Masayoshi Mase1, Hiroya Matsuba2 (1. Hitachi, Ltd., 2. Hitachi Power Solutions Co., Ltd.)
[4Yin-A-27]Analysis of the Influence of Input Granularity on TTP Extraction from CTI Reports
〇Hiroyoshi Nagao1, Tomoaki Mimoto1, Takamasa Isohara1 (1. KDDI Research, Inc.)
[4Yin-A-28]Factor Analysis of Contextual Hallucinations Classification by a Linear Classifier Using Lookback Ratio Features
〇Yuto Sasaki1, Kenya Jin'no1 (1. TOKYO city univercity)
[4Yin-A-29]Enhancing Label Quality and Generalization through Additional Supervision
〇Kosuke Sugiyama1, Masato Uchida1 (1. Waseda University)
[4Yin-A-30]Human-in-the-Loop Jailbreak Attacks via Token Candidates from Multiple Generation Sources
〇Manato Ito1, Hiroki Kinoshita2, Kazuki Iwahana2, Toshiki Shibahara2, Masato Uchida1 (1. Waseda University, 2. NTT Social Informatics Laboratories)
[4Yin-A-31]Label Noise Vulnerability of Fixed ETF Classifiers in Imbalanced Environments and Robustness Enhancement via Label Smoothing
〇Koya Funahashi1, Masato Uchida1 (1. Waseda University)
[4Yin-A-32]Soft Label Construction via Integration of Confidence and Neighborhood Information
〇Mao Iwasaki1, Kosuke Sugiyama1, Masato Uchida1 (1. Waseda University)
[4Yin-A-33]Residual Learning Framework for Time Series Forecasting Based on Naive Baselines
〇Chihiro Mihara1 (1. The Graduate University for Advanced Studies (SOKENDAI))
[4Yin-A-34]Differentiable Dynamic Top-k with Convex Optimization
〇Tomoya Uekita1, Kyohei Atarashi1, Koh Takeuchi1, Hisashi Kashima1 (1. Kyoto University)
[4Yin-A-35]Exploring Message Customization for Driver Assistance Functions Based on Driving-Context TIPI-J and Personality Characteristics
〇Makoto Sei1 (1. TOYOTA MOTOR CORPORATION)
[4Yin-A-36]Autonomous Emergence of Communication Strategies in World Model-based Multi-Agent Reinforcement Learning
〇Yuya Kamezawa1 (1. The University of Electro-Communications)
[4Yin-A-37]Transfer Learning Approaches for Sequential Sentence Classification in Japanese Abstracts
〇Kazuhiro Yamauchi1, Waka Yasuo1, Marie Katsurai1 (1. Doshisha University)
[4Yin-A-38]Bottom-Up Interpretation of Language Model Training Dynamics via Loss Curve Clustering
〇Koshiro Aoki1,2, Masaru Isonuma2,3,4, Yusuke Oda2, Hirokazu Kiyomaru2, Takashi Kodama2, Chaoran Liu2, Yohei Oseki4,2, Yusuke Miyao4,2, Daisuke Kawahara1,2 (1. Waseda University, 2. NII LLMC, 3. Tohoku University, 4. Univ. of Tokyo)
[4Yin-A-39]Fairness Evaluation in Recruitment using LLMs: Analysis of Job Selection Bias through Simulated Personalities
〇Kosuke Kitahara1 (1. Recruit Co., Ltd.)
[4Yin-A-40]Analysis of Emergence Trends and Distribution of Intruder Dimensions in Large Language Models
〇Miyuki Toyoi1, Bowen Chen1, Namgi Han1, Miyao Yusuke1,2 (1. The University of Tokyo, 2. Research and Development Center for Large Language Models, National Institute of Informatics)
[4Yin-A-41]Offensive Value Evaluation in Soccer Based on Ball Locations and Goal Probability Distributions Following Line Breaks
〇Shoma Yagi1, Jun Ichikawa1, Genki Ichinose1 (1. Shizuoka University)
[4Yin-A-42]Study of an Automated Particle Detection Method in Particle Analysis Processes Using TEM Images
〇Koushi Shinohara1, Keiichirou Nayuki1, Masahide Shima1, Nobuaki Tanabe1, Masahiko Takei1 (1. JEOL Ltd.)
[4Yin-A-43]Evaluating the Effectiveness of Japanese Pretraining and Fine-Tuning for Language Models with Neural Long-Term Memory Modules
〇Yuki Shimoda1, Yoshinobu Kano1 (1. Shizuoka University)
[4Yin-A-44]Analyzing Training Data Contributions in LLM Pretraining via Parameter-Space Distance
〇Yuto Nishida1,2, Hirokazu Kiyomaru2, Yusuke Oda2, Takashi Kodama2, Chaoran Liu2, Daisuke Kawahara3,2, Yusuke Miyao4,2, Masaru Isonuma2,5 (1. Nara Institute of Science and Technology, 2. Research and Development Center for Large Language Models, National Institute of Informatics, 3. Waseda University, 4. The University of Tokyo, 5. Tohoku University)
[4Yin-A-45]Automated Gap-Filling in Formal Proofs Using Large Language Models
〇JUNYANG PAN1, TUSUYA MATUZAKI1 (1. Tokyo University of Science)
[4Yin-A-46]Analysis of the Neglect-Zero Effect in Large Language Models
〇Jin Tanaka1, Daiki Matsuoka1,2, Ryoma Kumon1,2, Hitomi Yanaka1,2,3 (1. The University of Tokyo, 2. RIKEN, 3. Tohoku University)
[4Yin-A-47]Tacit Knowledge Candidate Span Extraction from Procedural Videos via Question-Based Verification
Tsukasa Kamo1, 〇Keigo Yoshida1, Atsushi Kuboya1, Yuji Ayusawa1, Tatsuya Yamamoto1, Yusuke Yamashina2, Caio Cesar Pinheiro de Moura2, Keisuke Niimi2, Kazuma Shiomi2 (1. SCSK Corporation, 2. Insight Edge, Inc.)
[4Yin-A-48]Verbalization of Tacit Knowledge through Dynamic Nuance Analysis in Videos Using Multimodal Large Language Models
〇Tatsuya Yamamoto1, Atsushi Kuboya1, Yuji Ayusawa1, Tsukasa Kamo1, Keigo Yoshida1, Yusuke Yamashina2, Keisuke Niimi2, Caio Cesar Pinheiro de Moura2, Kazuma Shiomi2 (1. SCSK Corporation, 2. Insight Edge , Inc)
[4Yin-A-49]Applying Batch Normalization Re-training in Transfer Learning to Class-Incremental Learning
〇Chika Obata1, Sora Togawa1, Kenya Jinno1 (1. Tokyo City University)
[4Yin-A-50]Mitigating Visual Attention Sink and Reducing Hallucination Using Soft Registers in Large Vision-Language Models
〇Satsuki Tamura1, Takashi Shibata1, Atsumasa Tsukie1, Jun Miyazaki1, Shota Takano1, Kazuko Nakayama1 (1. NTT EAST, Inc)
[4Yin-A-51]Direct–Reverberant Sound Separation with Spatial Information Awareness Based on Deep Learning and the Sparse Equivalent Source Method
〇Meika Iwamatsu1, Ryosuke Onizawa1, Ayame Uchida1, Izumi Tsunokuni1, Yusuke Ikeda1 (1. Tokyo Denki University)
[4Yin-A-52]A Study on Skill Level Classification and Biomechanical Validity of Basketball Shooting Motions Using Motion Data
〇Iori Furuya1, Kazuya Tomabechi2, Tatsuki Seino3, Rui Miyazawa4 (1. Yokohama City University, 2. The University of Tokyo, 3. Graduate School of Information Science and Technology Hokkaido University, 4. sci-bone Corporation)
[4Yin-A-53]Construction of a Web UI Operation Dataset with Ambiguous Natural Language Instructions Containing Degree Adverbs
〇Yamamoto Hiromu1 (1. Waseda University)
[4Yin-A-54]Impact of Cognitive Bias-Driven DM Design Optimization on Store Visits and Purchases Behavior
〇Koya Tsukamoto1, Kaori Kumagai1, Yukiko Yoshikawa1, Masaaki Miura1, Takuya Yamada1, Takashi Suzuki1 (1. NTT DOCOMO INC.)
[4Yin-A-55]Automated Crosswalk Toward Greater Interoperability in AI Safety
〇Takayuki Semitsu1,2, Naoto Kiribuchi1,2, Kengo Zenitani1,2, Hikaru Matsuoka3,1,2 (1. Japan AI Safety Institute, 2. Information-technology Promotion Agency, 3. RIKEN Center for Advanced Intelligence Project)
[4Yin-A-56]Narrative Annotation: Dynamic Question Planning in Open-Domain Dialogue
〇Kenta Hama1, Atsushi Otsuka1, Kazuya Matsuo1, Shinichiro Eitoku1, Narichika Nomoto1 (1. Human Informatics Laboratories, NTT, Inc.)
[4Yin-A-57]Zero-Shot Triggering of Homograph Reading with Brackets using Pre-trained T5 Language Models
〇Tomoya Hirata1, Kazuhiro Takeuchi1 (1. Osaka Electro-Communication University)
[4Yin-A-58]Assigning personality traits to reasoning models via their thought processes
〇Tetsuya Hashimoto1, Mitsuhiro Mabuchi1, Miki Ota2, Taisei Ozaki2 (1. TOYOTA MOTOR CORPORATION, 2. MATSUO INSTITUTE, INC)
[4Yin-A-59]Analysis of Japanese Modern Criticism using Large Language Models
〇Itsuki Kanemura1, Ryosuke Yamaki1, Azusa Sasaki1 (1. Ritsumeikan University)
[4Yin-A-60]Development of a Dialogue System Capable of Real-Time Backchanneling
〇Sho Katsuki1, Yoshinobu Kano1 (1. Shizuoka University)
[4Yin-A-61]A Multi-Agent Design for Educational Dialogue Systems Enabling Adherence to Predefined Complex Learning Scenarios
〇Haruki Hikino1, Tomoki Kera1, Kristiina Jokinen2,3,1, Sven Kirsch, Chung-Chi Chen3, Atsushi Keyaki1 (1. Hitotsubashi University, 2. University of Helsinki, 3. National Institute of Advanced Industrial Science and Technology)
[4Yin-A-62]Memory Governance for Cross-Session Prohibition Retention
〇Yu Amano1 (1. Activarch Consulting)
[4Yin-A-63]Proposal for an Automated Thematic Stock Selection Method Using an Autonomous Web-Exploration Agent
〇Mitsutoshi Matsudo1, Takehiro Takayanagi1,3, Noriaki Saito1,2, Yuri Murayama1, Kiyoshi Izumi1 (1. Univ. of Tokyo, 2. Global X Japan Co. Ltd., 3. Simulacra Inc.)
[4Yin-A-64]An Attempt at Human Mobility Data Generation using Movement Pattern Extractinon and LLMs
〇Shohei Takase1, Hiroki Sakaji1, Itsuki Noda1 (1. Hokkaido University)
[4Yin-A-65]Analyzing the Diffusion Structure of Social Media Posts Related to Political StatementsA case study of the statement, “Older women cannot bear children.
〇Yudai Taguchi1, Yoshinobu Kano1 (1. shizuoka university)
[4Yin-A-66]Development of an LLM-Based Word Wolf Agent Considering Semantic Similarity Between Words
〇Soka Matsugaki1, Yunoka Yamamoto1, Ryusei Nishio1, Joji Suzuki1, Ayuki Kuruko1, Reon Ohashi1, Kazuya Tsubokura1, Kunikazu Kobayashi1 (1. Aichi Prefectural University)
[4Yin-A-67]Development of LLM-based Agents in Japanese Murder Mystery Games and Quantitative Analysis of Dialogue Logs
〇Ryusei Nishio1, Yunoka Yamamoto1, Soka Matsugaki1, Joji Suzuki1, Ayuki Kuroko1, Reon Ohashi1, Kazuya Tsubokura1, Kunikazu Kobayashi1 (1. Aichi Prefectural University)