Synthetic training data designed to break the correlation between semantic and preferential signals in text embeddings provably improves preference prediction across 11 online deliberation datasets.
American Political Science Review , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Embeddings for Preferences, Not Semantics
Synthetic training data designed to break the correlation between semantic and preferential signals in text embeddings provably improves preference prediction across 11 online deliberation datasets.