アウトプット実績

  • 国際

    Frontiers in Psychology

    ,

    Online harassment of Japanese celebrities and influencers

  • 国際

    Journal of Physics: Complexity

    ,

    Pacemaker effects on online social rhythms on a social network

  • 国際

    Stochastic Networks conference (SNC)

    On Universally Optimal Algorithms for A/B Testing

  • 国際

    ICML 2024 Workshop: Models of Human Feedback for AI Alignment (ICML 2024 Workshop : Models of Human Feedback for AI Alignment, MHF)

    Filtered Direct Preference Optimization

  • 国際

    ICML 2024 Workshop: Models of Human Feedback for AI Alignment (ICML 2024 Workshop : Models of Human Feedback for AI Alignment, MHF)

    Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment

  • 国際

    Transactions of the Association for Computational Linguistics (TACL)

    Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding

  • 国際

    PRX Life (PRX Life)

    Who is a leader in the leading eight? –indirect reciprocity under private assessment–

  • 国際

    Global Evidence Summit ( グローバルエビデンスサミット, GES)

    Can a generative AI chatbot answer citizens’ questions on behalf of municipal employees?

  • 国際

    Workshop on Cross-Cultural Considerations in NLP (C3NLP)

    Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?

  • 国際

    Parallel Problem Solving from Nature (PPSN)

    CMA-ES for Discrete and Mixed-Variable Optimization on Sets of Points