Polarity Composition Hypothesis: Causal Evidence from Negation in NLI

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.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-17
DOI
https://doi.org/10.48550/arxiv.2611.23185
Primary Topic
Topic Modeling
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Polarity Composition Hypothesis: Causal Evidence from Negation in NLI

Tatsuya Hiraoka, Munachiso Samuel Nwadike, Kentaro Inui, Nhi Hoai Doan
arXiv (Cornell University)
Topic Modeling
preprint

Polarity Composition Hypothesis: Causal Evidence from Negation in NLI

Tatsuya Hiraoka, Munachiso Samuel Nwadike, Kentaro Inui, Nhi Hoai Doan
preprint en

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.

arXiv (Cornell University)
Topic Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon