AI Tools & Models HOTFeaturedAll
arXiv cs.AIScore60

Pluralistic Alignment in Large Language Models: Objectives, Human References, and Preference Representations

Summary

Rather than squeezing diverse human preferences into one target, alignment should keep meaningful differences intact, the work argues.

Why this matters

Covers model · Relevant to this topic

Open original ↗

Source: arXiv cs.AI · arxiv.org

Topics

Related items