PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment

Daiwei Chen, Yi Chen, Aniket Rege, Zhi Wang, Ramya Korlakai Vinayak
2/12/2026

No official code found. Best implementation: RamyaLab/pluralistic-alignment (16 stars, Apache-2.0, last commit 2025-08-28).

Semantic Scholar

Code Implementations(1)

RamyaLab/pluralistic-alignmentCommunity70%
Apache-2.0

The open-source repository for PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment.

162Python, Jupyter NotebookOct 9, 20241 years agoApache-2.0
ai-alignmentpluralistic-alignmentrlhf

Cite this paper

@article{chen2026pal,
  title  = {PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment},
  author = {Daiwei Chen and Yi Chen and Aniket Rege and Zhi Wang and Ramya Korlakai Vinayak},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:6a4005d51408bd98decd06d03e58763bcb3e1b29},
  journal = {ICLR 2025 2025}
}

Discussion