arXiv · 2611.23185
Polarity Composition Hypothesis: Causal Evidence from Negation in NLI
Abstract
We investigate how language models process negation in natural language inference (NLI). We propose the \textit{Polarity Composition Hypothesis}, a high-level causal model of this computation. Behavioral evaluations show that language-model predictions largely conform to the proposed hypothesis. Using Distributed Alignment Search, we identify causally effective subspaces aligned with the variables in the polarity-composition hypothesis. These representations transfer across negation forms and partially to a subset of MNLI. We release the dataset and code.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Nhi Hoai Doan, Tatsuya Hiraoka, Munachiso Samuel Nwadike, Kentaro Inui. 2026-11-17. Polarity Composition Hypothesis: Causal Evidence from Negation in NLI. https://searcharxiv.com/abs/2611.23185
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.