cd /news/natural-language-processing/polarity-composition-hypothesis-caus… · home › topics › natural-language-processing › article
[ARTICLE · art-172364] src=machinebrief.com ↗ pub= topic=natural-language-processing verified=true sentiment=· neutral

Polarity Composition Hypothesis: Causal Evidence from Negation in NLI

Researchers Nhi Hoai Doan, Tatsuya Hiraoka, Munachiso Samuel Nwadike and Kentaro Inui released arXiv paper 2611.23185v1 proposing the Polarity Composition Hypothesis, a high-level causal model of how language models process negation in natural language inference (NLI). Behavioral evaluations showed language-model predictions largely conform to the hypothesis, and using Distributed Alignment Search the authors identified causally effective subspaces aligned with the hypothesis's variables that transfer across negation forms and partially to a subset of MNLI. The authors released the dataset and code.

recommendation

Use Distributed Alignment Search to locate causally effective subspaces for the behavior you care about, then test whether the found representations transfer across input variants and out-of-distribution subsets before relying on them.

more in playbook: Evals and testing for LLM apps
by read1 min views3 publishedNov 19, 2026
Polarity Composition Hypothesis: Causal Evidence from Negation in NLI
Image: Machinebrief (auto-discovered)

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.

── more in #natural-language-processing 4 stories · sorted by recency
── more on @nhi hoai doan 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/polarity-composition…] indexed:0 read:1min 2026-11-19 · —