SOURCE-LINKED INTELLIGENCE

Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable structures. This paper explores whether NLI can be performed using only interpretable, graph-based representations of evidence. We introduce a fully graph-based pipeline where the classifier never directly processes the input text. Instead, sentences are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and represented as three graphs per pair: premise, hypothesis, and a retrieved ConceptNet subgraph

Read original source ↗ Open in workspace

recordType

paper

region

Global