By Nhi Hoai Doan, Tatsuya Hiraoka, Munachiso Samuel Nwadike, Kentaro InuiSource:
[arXiv cs.CL](https://arxiv.org/list/cs.CL/recent)
arXiv:2611.23185v1 Announce Type: new
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. Get AI news in your inbox
Daily digest of what matters in AI.