[1L3-OS-34] OS-34

Tue. May 27, 2025 1:40 PM - 3:20 PM Room L (Room 1007)

オーガナイザ：林祐輔（AIアライメントネットワーク），坂本航太郎（東京大学），和地瞭良（LINEヤフー），阿部拳之（サイバーエージェント），森村哲郎（サイバーエージェント）

+Add all to schedule

1:40 PM - 2:00 PM

[1L3-OS-34-01] Aligning Japanese Large Language Models through Self-Improvement: An Empirical Study

〇Mitsuki Sakamoto¹, Yu Jinnai¹, Tetsuro Morimura¹, Kenshi Abe¹, Kaito Ariu¹ (1. CyberAgent)

2:00 PM - 2:20 PM

[1L3-OS-34-02] Strategy Evolution in Repeated Donation Games among Large Language Model

〇Kazuya Horibe¹, Wataru Toyokawa¹ (1. RIKEN)

2:20 PM - 2:40 PM

[1L3-OS-34-03] Learning in Periodic Zero-Sum Games

Synchronization Triggers Divergence from Nash equilibrium

〇Yuma Fujimoto^1,2,3, Kaito Ariu¹, Kenshi Abe^1,4 (1. CyberAgent, 2. University of Tokyo, 3. Soken University, 4. University of Electro-Communications)

[[Online]]

2:40 PM - 3:00 PM

[1L3-OS-34-04] Designing Alignment Filters for Large Language Models with Existing Evaluation Models

〇Yuya Miyaoka¹, Masaki Inoue¹ (1. Keio University)

3:00 PM - 3:20 PM

[1L3-OS-34-05] Modeling Interaction Between Large Language Models and Humans in Co-Creative Decision-Making as Distributed Bayesian Inference

〇Momoha Hirose¹, Tadahiro Taniguchi^1,2 (1. Kyoto University, 2. Ritsumeikan University)

Session information