Session Details
[5Yin-A]Poster 8
Fri. Jun 12, 2026 12:30 PM - 2:00 PM JST
Fri. Jun 12, 2026 3:30 AM - 5:00 AM UTC
Fri. Jun 12, 2026 3:30 AM - 5:00 AM UTC
Room Y(Exhibition hall AB 1)
[5Yin-A-01]Evaluating CRM Campaign Effects with Distributional Treatment Effects
〇Masahiro Tanaka1, Asuto Hirano1, Shota Yasui1 (1. CyberAgent)
[5Yin-A-02]Proposal on Refining Synthetic Data Based on User Feedback to Recommender Systems
〇Takumi Miyazawa1, Hiroki Shibata1, Yasufumi Takama1 (1. Tokyo Metropolitan University)
[5Yin-A-03]Time-Series Analysis of Customer Demographics of Restaurant Chains Based on Mobile Carrier Search Logs
〇Daichi Inoue1, Hayato Mori2, Taketoshi Yoshii1, Sadakazu Kinoshita1, Daichi Mochihashi3 (1. D2C Inc, 2. NTT DOCOMO, INC, 3. The Institute of Statistical Mathematics)
[5Yin-A-04]Mitigating Negative Transfer in Multi-Domain Sequential Recommendation with LLM-based Mixture of Experts
〇Hayata Shimizu1, Koichi Shinoda1, Motomura Yoichi2 (1. Science Tokyo, 2. National Institute of Advanced Industrial Science and Technology)
[5Yin-A-05]An Investigation and Analysis of an Uncertainty Indicator Based on Non-Relevance Score for Pointwise Re-ranking
〇Akihiro Katsuno1, Yuichiro Okugawa1, Toshimitsu Tanaka1, Tomomi Nagao1, Hiroaki Kawata1 (1. NTT, Inc.)
[5Yin-A-06]Dynamic User Profiling in GaaS Community Backlash: A Hybrid Framework for Risk Detection and SegmentationDifferentiating Core Players from External Interference in Genshin Impact
〇Yanming He1,2, Hideaki Takeda2,1 (1. Graduate University for Advanced Studies, SOKENDAI, 2. National Institute of Informatics)
[5Yin-A-07]An Analysis of Evaluation Characteristics Using LLM-as-a-Judge for Future Scenario Generation
〇Tomomi Nagao1, Yuichiro Okugawa1, Toshimitsu Tanaka1, Akihiro Katsuno1, Hiroaki Kawata1 (1. NTT, Inc.)
[5Yin-A-08]Interpretable Modeling of Organic Materials Synthesis Using Computational Chemistry Descriptors and Machine Learning
〇Kiho Matsubara1, Ryohei Kakuchi1, Takeshi Matsuda2, Kei Takahashi3, Noriaki Seko4, Masaaki Omichi4 (1. Gunma Univ., 2. Hannan Univ., 3. Osaka Metropolitan Univ., 4. QST-Takasaki)
[5Yin-A-09]Proposal of an Proactive Speech Timing Estimation Method Using Audio, Visual Field Images, and Head Inertial Information
〇Naomasa Itakiyo1, Kazuya Mera1, Yoshiaki Kurosawa1, Toshiyuki Takezawa1 (1. Hiroshima City University)
[5Yin-A-10]Efficient Offline Learning of Ranking Policies via Top-k Policy Decomposition
Ren Kishimoto2, 〇Koichi Tanaka1, Haruka Kiyohara4, Yusuke Narita5, Nobuyuki Shimizu3, Yasuo Yamamoto3, Yuta Saito4 (1. Keio University, 2. Institute of Science Tokyo, 3. LY Corporation, 4. Cornell University, 5. Yale University)
[5Yin-A-11]Performance Analysis of Code LLMs between Japanese and English Prompts Using JEvalPlus
〇Mai Takahashi1, Hiroshi Kazato1, Kyosuke Nishida1 (1. NTT, Inc.)
[5Yin-A-12]Evaluation of Money Laundering Detection Accuracy Considering Information Asymmetry: Quantitative Evaluation Using Simulation Data
〇Shoichiro Sekiguchi1, Miho Sugi1, Masayuki Komai1, Hirokazu Koma1 (1. SimpleForm, Inc.)
[5Yin-A-13]The Impact of Regulatory Reforms for Annual Securities Reports on Risk Disclosure
〇Nobuhiro Aikawa1, Mitsuo Yoshida1 (1. University of Tsukuba)
[5Yin-A-14]Bifurcation prediction using reservoir computing and its performance evaluation
〇Lingfeng Chen1, Masanobu Inubushi1,2 (1. Tokyo University of Science, 2. The University of Osaka)
[5Yin-A-15]Exploring Feedback-Driven Text Optimization for User-Level Fixed-Allocation A/B Testing
〇Masashi Ueno1, tetsu sato1, Naohiro Ikahata1 (1. PERSOL CAREER CO., LTD.)
[5Yin-A-16]ShigyoBench: Construction and Performance Evaluation of an LLM Benchmark for Japanese Professional Licensing Examinations
〇Masato Todo1, Shin-nosuke Ishikawa1,2 (1. MAMEZO Co., Ltd., 2. Rikkyo University)
[5Yin-A-17]A Semantic Search System for National Tax Tribunal Decisions Based on Large Language Model Embeddings
〇Ryuya Yamagishi1, Fumikatsu Anaguchi1, Takeshi Morita1 (1. AOYAMA GAKUIN UNIVERSITY)
[5Yin-A-18]Does Generative AI Homogenize Writing Style?
〇Yuika Miura1, TETSUJI KUBOYAMA1 (1. Gakushuin University)
[5Yin-A-19]A Threat Intelligence-Driven Jailbreak Defense Framework Based on Kill Chain Modeling and Attack Phase Tracking
〇Yusuke Akimoto1, Hisashi Okui1, Yutaro Iizawa1 (1. ARISE analytics)
[5Yin-A-20]Simulating "Refusal" in Dementia Care: Constructing Role-Play Language Agents for Caregiver Training
〇Rafael Mugi Suzuki1, Yohei Kobashi2 (1. Tohoku University, 2. The University of Tokyo)
[5Yin-A-21]Analysis of Discourse Characteristics of the 2025 LDP Presidential Election on Anonymous Local Bulletin Boards
〇MITSUO YOSHIDA1 (1. University of Tsukuba)
[5Yin-A-22]Building a Prediction Model for Commercial Value of Web Novels Using LightGBM and Feature Analysis
〇Kenichiro Ohta1, Mitsuo Yoshida1 (1. University of Tsukuba)
[5Yin-A-23]Sales Uplift Prediction for Point-Based Promotion Campaigns in an Online Travel Agency
〇Jiheng Sun1, Hisashi Kashima1, Koh Takeuchi1, Kyohei Atarashi1, Ryo Matsui2, Shusaku Yoshizumi2, Shunji Umetani2 (1. Kyoto University, 2. Recruit Co., Ltd.)
[5Yin-A-24]Assessment of AI Applicability in GMP Compliant Cell Manufacturing for Regenerative Therapy based on PIC/S GMP Annex 22
〇yoshimi sugahara1, Masayoshi Tsukahara1 (1. CiRA Foundation)
[5Yin-A-25]Parameter estimation of an ECG model based on delay-coupled oscillators using physics-informed neural networks
〇Daiki Watanabe1, Kentaro Takeda1 (1. Kagawa University)
[5Yin-A-26]Irrational Clinical Decision-Making of Large Language Models in Uncertain Medical Scenarios: A Prospect Theory–Based Analysis
〇Ryota Shibaki1,2, Kazuma Kobayashi1,2, Hiromi Matsumoto1,2, Ryuji Hamamoto1,2 (1. National Cancer Center Research Institute, 2. RIKEN Center for Advanced Intelligence Project)
[5Yin-A-27]Corporate Feature Extraction from Annual Securities Reports Using Clustering and LLM Evaluation
〇Yuichiro Okugawa1, Toshimitsu Tanaka1, Tomomi Nagao1, Akihiro Katsuno1, Hiroaki Kawata1 (1. NTT, Inc.)
[5Yin-A-28]Forecast as Intervention: Causal Performative Prediction for Congestion Forecast
〇Akira Tanimoto1, Koh Takeuchi2, Hisashi Kashima2 (1. Preferred Networks, Inc., 2. Kyoto University)
[5Yin-A-29]Cross-Robot Knowledge Transfer for Quadrupedal Control via In-Context Reinforcement Learning
〇Naoaki Ishii1, Hiroshi Kera1,2, Kazuhiko Kawamoto1 (1. Chiba University, 2. National Institute of Informatics)
[5Yin-A-30]Evaluation of Distributional Matching of Substructures in Language-Model-Based Graph Generation
〇Masatsugu Yamada1, Mahito Sugiyama1 (1. National Institute of Informatics)
[5Yin-A-31]Information-Equilibrated Distributionally Robust Alternating Optimization for Risk-Sensitive Search
〇Chikara Hoshino1 (1. BIPROGY Inc.)
[5Yin-A-32]Improvement of Computational Efficiency and Explainability by Sparse Binary Neural Networks
〇Taketo Shibata1, Kunikazu Kobayashi2 (1. Graduate School of Aichi Prefectural University, 2. Aichi Prefectural University)
[5Yin-A-33]User Profile Optimization Considering Ranking Difficulty of Recommendation Candidates in LLM-based Recommendation Systems
〇Taichi Sakaguchi1, Kazuki Kozuka1, Kouhei Yamanishi1, Tomoka Ikeda2, Takashi Bando1 (1. Panasonic Holdings Corporation, 2. Panasonic Corporation)
[5Yin-A-34]The Effect of Population Size on Cultural Accumulation using Multi-Agent Reinforcement Learning
〇Manato Naito1, Kei Wakabayashi1 (1. University of Tsukuba)
[5Yin-A-35]A study on generating explanations for diagrams and tables to predict correct answer rates in mock exams
〇KAORU HIRAMATSU1 (1. Saitama University)
[5Yin-A-36]Semantic Similarity–Based Initialization of Embeddings for Novel Concepts
〇Toko Miura1, Masaya Taniguchi2,1, Tatsuya Hiraoka3,2,4, Keisuke Sakaguchi1,2, Kentaro Inui3,1,2 (1. Tohoku University, 2. RIKEN, 3. Mohamed bin Zayed University of Artificial Intelligence, 4. Nara Institute of Science and Technology)
[5Yin-A-37]Model Robust Learning of Modular Addition
〇Hanato Kikuchi1, Kazuhiko Kawamoto1, Hiroshi Kera1,2 (1. chiba university, 2. National Institute of Informatics)
[5Yin-A-38]Optimizing High-Dimensional Review Features: Via LLM Semantic Extraction and Lightweight mRMR Feature Selection Network Architecture
〇Hengshuo Yang1, Tengfei Shao1, Masayuki Goto1 (1. Waseda University)
[5Yin-A-39]Analyzing the Impact of Multimodal Features on Learner Satisfaction in Long-duration Training
〇Kaede Mori1, Taishi Watanabe2, Yusuke Yamamoto2, Hayate Funakura1,3, Ryo Kinoshita1 (1. Kikagaku, Inc., 2. Ricoh Company, Ltd., 3. Keio University)
[5Yin-A-40]An Experimental Study on the Introduction of AI for Feedback on Goal Setting
〇Takumi Nakai1, Yoshitaka Hirose2 (1. Osaka Metropolitan University, 2. Doshisha University)
[5Yin-A-41]Joint Optimization of Merge Parameters and Quantization Bit-Width in Model Merging
〇Tomoya Ozone1, Rio Akizuki1, Kento Uchida1, Shinichi Shirakawa1 (1. Yokohama National University)
[5Yin-A-42]Operation Optimization of Renewable Energy Aquaculture based on the Grey Wolf Optimizer
〇Junchao Cheng1, Kazunori Mizuno1 (1. Takushoku University)
[5Yin-A-43]Generative Modeling of Low-Frequency Tremors Using Neural SDEs
〇Toshiro Kusui1, Hiromichi Nagao2,1,3, Shin-ichi Ito2,1, Shinya Katoh2 (1. Graduate School of Information Science and Technology, The University of Tokyo, 2. Earthquake Research Institute, The University of Tokyo, 3. RIKEN Center for Advanced Intelligence Project)
[5Yin-A-44]Goal-oriented Exploration in Continuous Control Tasks
Shoma Ogawa1, 〇takuma kuroda2, Takumi Kamiya2, Tatsuji Takahasi2, Yu Kohno2 (1. Graduate School of Tokyo Denki University, 2. Tokyo Denki Univercity)
[5Yin-A-45]Self-Generated QA Problems for Unlearned Knowledge in LLMs
〇Waka Ito1, Karin Yamashita1, Haruka Tsuchida1, Yuha Nishigata1, Kimio Kuramitsu1 (1. Japan Women's University)
[5Yin-A-46]A Motivational Interviewing Dialogue System using Multimodal RAG
〇Kazuma Kudo1, Jie Zeng1, Fumio Nihei1, Yukiko Nakano1 (1. Seikei University)
[5Yin-A-47]Abstain-aware Reinforcement Learning for Reasoning Large Language Models
〇Masaya Tsunokake1, Hikaru Tomonari1, Ryoichi Takase1, Koki Takeshita1, Masaharu Ukeda1, Yasuhiro Sogawa1 (1. Hitachi, Ltd.)
[5Yin-A-48]Evaluation of LLMs' Resistance to Induction Using an NG Word Game
〇Shunichi Yoneda1, Yukitake Yoshioka1, Yurai Takayanagi1, Yumi Fukuda1, Ryoma Obara4, Yusuke Sakai2, Hidetaka Kamigaito2, Katsuhiko Hayashi3, Shogo Matsuno1 (1. University of Electro Communications, 2. NAIST, 3. The University of Tokyo, 4. NEC)
[5Yin-A-49]Dataset Construction for Verifying Domain Separability in Internal Representations of Large Language Models
〇Daichi Yano1, hirotoshi taira1 (1. Osaka institute of technology)
[5Yin-A-50]Decoding Words with Different Pitch Accent Patterns from Brain Activity based on EEG Analysis
〇Hikari Nomura1, Kazuya Tsubokura1, Yurie Iribe1 (1. Aichi Prefectural University)
[5Yin-A-51]Context-Aware Fact-Opinion Classification in Newspaper Editorials for NIE Support
〇Takumi Kawahara1, Kazuaki Ando1 (1. Kagawa University)
[5Yin-A-52]Analysis of Personalized Care Quality Based on Structured Care Records Utilizing Large Language Models
〇Sakura Yui1, Atushi Omata1,2, Ai Okazaki3, Shogo Ishikawa1 (1. Shizuoka University, 2. Hamamatsu University School of Medicine, 3. Tomesan-chi)
[5Yin-A-53]Fundamental Study on Data Shapley-based Pseudo-Labeling via Neural Tangent Kernel
〇Ryo Mitoma1, Takayuki Mukaeda1,2, Keisuke Shima1 (1. Yokohama National University, 2. Kanagawa Institute of Industrial Science and Technology)
[5Yin-A-54]Dataset Analysis for Multifaceted Fake News Evaluation
〇Akari Yoshida1, Kazuaki Ando1 (1. Kagawa University)
[5Yin-A-55]Evaluating Inference Accuracy Improvements in Causal Structure Estimation via Few-Shot Learning
〇Takuya Yasuda1, Eijiro Mochida1, Yuri Murayama1, Kiyoshi Izumi1 (1. The University of Tokyo Graduate School)
[5Yin-A-56]Generating Fill-in-the-Blank Questions Focused on Grammatical Structure: Verifying the Generative Capabilities of LLMs in the Japanese Programming Language “Nadeshiko”
〇Kazuki Nishii1, Kazuaki Ando1 (1. Kagawa University)
[5Yin-A-57]What AI is Truly Useful for Young People: Building the Japanese Youth Culture Benchmark SakuraQA
〇Manami Hasegawa1, Yuka Miyata1, Waka Ito1, Manaka Odagaki1, Yuha Nishigata1, Kimio Kuramitsu1 (1. Japan Women's University)
[5Yin-A-58]Learning to Compute Gröbner Bases using Transformers with Set FiLM
〇Fuga Takami1, Mizuka Komatsu1,2, Takenao Ohkawa1 (1. Kobe University, 2. RIKEN)
[5Yin-A-59]A Study on Response Generation Methods Based on Contradiction Detection with Target Person's Information in Specific-Person Imitation Dialogue
〇Hinano Koga1, Kohei Okuoka1, Kosuke Sasaki2, Hisashi Noda2, Masakazu Moriguchi2, Masahiko Osawa1 (1. Nihon University, 2. NEC Solution Innovators, Ltd.)
[5Yin-A-60]Revisiting the Role of Attention Weighting in Transformer-based Sequential Recommender Model
〇Keito Kozaki1, Keigo Sakurai2, Ren Togo3, Takahiro Ogawa3, Miki Haseyama3 (1. School of Engineering, Hokkaido University, 2. Data-Driven Interdisciplinary Research Emergence Department, Institute for Integrated Innovations, Hokkaido University, 3. Faculty of Information Science and Technology, Hokkaido University)
[5Yin-A-61]The Potential for Integrating Skills and Knowledge in Large Language Models
〇Haruka Tsuchida1, Yuha Nishigata1, Waka Ito1, Kimio Kuramitsu1 (1. Japan Women's University)
[5Yin-A-62]Performance Evaluation of Generative AI in Accounting and AuditingExperimental evidence from the Japanese CPA Auditing Examination
〇Yoshitaka Hirose1 (1. Doshisha University)
[5Yin-A-63]Evaluating LLM Reasoning Ability via the Gap Between Logical and Everyday Reasoning: A Comparison of Reasoning and Non-Reasoning Models
〇Kentaro Ozeki1,2, Hirohiko Abe1, Risako Ando1, Takanobu Morishita1, Koji Mineshima1, Mitsuhiro Okada1 (1. Keio University, 2. University of Tokyo)
[5Yin-A-64]Layer-wise Analysis of Emotion Representations in Large Language Models
〇Maho Hanaoka1 (1. *)