Paper Trail

Tag: eit-ningbo

1 item with this tag.

  • Mar 18, 2026

    The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models

    • paper
    • reward-model
    • eit-ningbo
    • hkpu
    • modality/text

Created with Quartz v4.5.2 © 2026

  • GitHub