For each survey question and target country, the framework selects relevant demographic attributes, constructs plausible groups using public population statistics, and generates multiple perspectives within each group.
Modeling within-group variation improves estimates of population opinion
An inference-time framework generated multiple demographically grounded perspectives and more closely matched survey distributions than several pluralistic-alignment baselines.
Big Tech
Meng-Chen Wu · Qipin Chen · Ansh Jain · Tess Wood · Zhe Du · Si-Chi Chin
Amazon Science
Research Digest··3 min read
Wu and colleagues introduce Demographic Pluralism, a framework for estimating how opinions are distributed across a population without training or calibrating on observed opinion distributions.
Why this paper
From Amazon Science
In one line
Generating multiple perspectives within demographically grounded groups estimates population opinion distributions more accurately than Modular Pluralism without opinion-distribution training data or task-specific fine-tuning.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§