1 Matching Annotations
  1. Jan 2025
  2. openreview.net openreview.net
    1
    1. mark.crowley 31 Jan 2025

      MAPPING SOCIAL CHOICE THEORY TO RLHF Jessica Dai and Eve Fleisig ICLR Workshop on Reliable and Responsible Foundation Models 2024

      Nice overview of how social choice theory has been connected to RLHF and AI alignment ideas.

      #ai-morality align rlhf llm #reinforcement-learning
    Visit annotations in context

    Tags

    Annotators

    URL

    openreview.net/pdf