Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?
Published 18 Sept 2026arXiv:2609.16814
Updated 4 h ago · first seen 16 Sept 2026
paper_01M2PPQEMPZ95529KMBQG0D973
Abstract
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. These graphs are then fed into a fine-tuned 0.8-billion-parameter language model. On the SNLI dataset, our pipeline achieves 89.7% accuracy, just 1.9 points below an identically trained text-based model. On ANLI, it matches the published performance of RoBERTa-large on rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) but trails by 16 points on R1, resulting in an overall gap of 9 to 14 points compared to its text counterpart. We term this gap the price of interpretability and demonstrate that it stems from representational limitations rather than data constraints. Ablation studies further reveal that graphs and text are complementary: combining both modalities achieves 92.1% accuracy on SNLI.
Organizations
Organizations 0
No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 4
Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?: published at changed from 2026-09-17T04:00:00+00:00 to 2026-09-18T04:00:00+00:00
Published17 Sept 2026→18 Sept 2026arxivCan We Do Interpretable NLI with Graphs Based on Atomic Propositions?: arxiv announce type changed from new to replace
Arxiv announce typenew→replacearxivCan We Do Interpretable NLI with Graphs Based on Atomic Propositions?: published at changed from 2026-09-16T04:00:00+00:00 to 2026-09-17T04:00:00+00:00
Published16 Sept 2026→17 Sept 2026arxivNew paper: Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?
arxiv
Sources
Sources 1
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.