cs.CLNov 17, 2026
SavePolarity Composition Hypothesis: Causal Evidence from Negation in NLI
Organizations: Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · RIKEN
Abstract
We investigate how language models process negation in natural language inference (NLI). We propose the 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.
More in this topic
Natural Language Inference
Natural language inference studies whether a premise entails, contradicts, or is unrelated to a hypothesis.
See all 47 papers