@misc{indiciaee0f460d2d20a,
  title = {Oracle-RLAIF: An Improved Multi-Modal Fine-Tuning Framework through Reinforcement Learning from Ranking Feedback},
  author = {Shi, Derek [University of California Los Angeles] and Glatt, Ruben [Lawrence Livermore National Laboratory] and Klymko, Christine [Lawrence Livermore National Laboratory] and Mohole, Shubham and Kushwaha, Shashank and Choi, Hongjun [Lawrence Livermore National Laboratory] and Sakla, Wesam [Lawrence Livermore National Laboratory] and Leno Da Silva, Leno [Lawrence Livermore National Laboratory]},
  year = {2026},
  doi = {10.2172/3389288},
  url = {https://www.osti.gov/biblio/3389288},
  note = {Source identifier: 3389288}
}