Papers with community LMs
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration (2024.emnlp-main)
Copied to clipboard
Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher, Chan Young Park, Yejin Choi, Yulia Tsvetkov
| Challenge: | Existing alignment paradigms for large language models learn an averaged human preference and struggle to model diverse preferences across cultures, demographics, and communities. |
| Approach: | They propose a modular framework that "plugs" into a base LLM a pool of smaller but specialized community LMs where models collaborate in distinct modes to support three modes of pluralism: Overton, steerable, and distributional. |
| Outcome: | The proposed framework “plugs into” a base LLM a pool of smaller but specialized community LMs, where models collaborate in distinct modes to support three modes of pluralism: Overton, steerable, and distributional. |
CommunityLM: Probing Partisan Worldviews from Language Models (2022.coling-1)
Copied to clipboard
| Challenge: | Political polarization is accelerating as political discourse diverges linguistically . et al. ( 2017) show that partisanship makes reliable predictions about an individual's word understanding . |
| Approach: | They propose a framework that probes community-specific responses to a survey using community language models CommunityLM. |
| Outcome: | The proposed framework can query the worldview of any group of people given a sufficiently large sample of their social media discussions or media diet. |