Center for Advanced Intelligence Project

2 papers have been accepted at COLM 2025 (Conference on Language Modeling) (Oct. 7-10, 2025, Montreal, Canada). For more details, please refer to the link below.

[COLM 2025] https://colmweb.org/

• Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human
  Feedback
  Johannes Ackermann (The University of Tokyo / RIKEN AIP)
  Takashi Ishida (RIKEN AIP / The University of Tokyo)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A
  Study with Context-Free Grammars
  Rei Higuchi (The University of Tokyo / RIKEN AIP)
  Ryotaro Kawata (The University of Tokyo / RIKEN AIP)
  Naoki Nishikawa (The University of Tokyo / RIKEN AIP)
  Kazusato Oko (UC Berkeley / RIKEN AIP)
  Shoichiro Yamaguchi (Preferred Networks, Inc.)
  Sosuke Kobayashi (Preferred Networks, Inc. / Tohoku University)
  Seiya Tokui (Preferred Networks, Inc.)
  Kohei Hayashi (The University of Tokyo)
  Daisuke Okanohara (Preferred Networks, Inc.)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)

Related Laboratories