Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
Authors:
Top Cited Papers
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 4151-4171
Abstract
Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher, Chan Young Park, Yejin Choi, Yulia Tsvetkov. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models2025
- REBEL: Reinforcement Learning via Regressing Relative Rewards2024
- CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies2024
- IterAlign: Iterative Constitutional Alignment of Large Language Models2024
- Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research2023
- Mixture of experts: a literature surveyArtificial Intelligence Review, 2012