pith. sign in

Liang, Ronan Le Bras, Katharina Reinecke, and Maarten Sap

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

years

2026 1 2024 2

verdicts

UNVERDICTED 3

roles

background 1

polarities

support 1

clear filters

representative citing papers

A Roadmap to Pluralistic Alignment

cs.AI · 2024-02-07 · unverdicted · novelty 6.0

The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • A Roadmap to Pluralistic Alignment cs.AI · 2024-02-07 · unverdicted · none · ref 284

    The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.

  • Inertia in Moral and Value Judgments of Large Language Models cs.CL · 2024-08-16 · unverdicted · none · ref 38

    LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.