7 papers
Offline Contextual Bandits in the Presence of New Actions
Ren Kishimoto, Tatsuhiro Shimizu, Kazuki Kawamura +6
Automated decision-making algorithms drive applications such as recommendation systems and search engines. These algorithms often rely on off-policy contextual bandits or off-polic…
PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows
Kazuki Kawamura, Satoshi Waki, Kei Tateno
Multi-agent LLM workflows -- systems composed of multiple role-specific LLM calls -- often outperform single-prompt baselines, but they remain difficult to debug and refine. Failur…
Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies
Koichi Tanaka, Kazuki Kawamura, Takanori Muroi +6
Off-Policy Evaluation (OPE) is an important practical problem in algorithmic ranking systems, where the goal is to estimate the expected performance of a new ranking policy using o…
LoopLens: Supporting Search as Creation in Loop-Based Music Composition
Sheng Long, Atsuya Kobayashi, Kei Tateno
Creativity support tools (CSTs) typically frame search as information retrieval, yet in practices like electronic dance music production, search serves as a creative medium for col…
Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning
Haruka Kiyohara, Yusuke Narita, Yuta Saito +2
In many real recommender systems, novel items are added frequently over time. The importance of sufficiently presenting novel actions has widely been acknowledged for improving lon…
Counterfactual Reciprocal Recommender Systems for User-to-User Matching
Kazuki Kawamura, Takuma Udagawa, Kei Tateno
Reciprocal recommender systems (RRS) in dating, gaming, and talent platforms require mutual acceptance for a match. Logged data, however, over-represents popular profiles due to pa…