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

• URL: http://arxiv.org/abs/2609.16814v1
• Date: Tue, 15 Sep 2026 08:20:20 GMT
• Title: Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?
• Abstract summary: This paper explores whether Natural Language Inference can be performed using only interpretable, graph-based representations of evidence.<n>We introduce a fully graph-based pipeline where the classifier never directly processes the input text.<n>On the SNLI dataset, our pipeline achieves 89.7% accuracy, just 1.9 points below an identically trained text-based model.
• Score: 2.6043470516146225
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 (50% accuracy) 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.

Related papers

• GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs [50.68372832207766]
  Graph Theory Bench (GT Bench) is a benchmark covering 24 classical graph problems in 44 task-structure settings.<n>GT Bench shows that accuracy is strongly tied to the input representation.<n>We propose the Graph Theory Agent (GTA), which pairs a preference-trained representation selector with plan-and-decompose scaffolding.
  arXiv  Detail & Related papers  (2026-09-10T22:50:10Z)
• ClosureBench: A Constructive Benchmark for Compositional Graph Reasoning [1.827510863075184]
  ClosureBench is a constructive benchmark for graph-relational reasoning with.<n> verified ground truth.<n>We evaluate models from 1.5B open weights to frontier systems.
  arXiv  Detail & Related papers  (2026-08-18T18:36:21Z)
• VeriGraph: Towards Verifiable Data-Analytic Agents [71.17693022916896]
  LLM-based agents have demonstrated strong capabilities in data-intensive analytical tasks, yet their outputs are rarely verifiable.<n>We propose VeriGraph, a traceable neuro-symbolic reasoning framework that enables agents to construct an explicit heterogeneous evidence directed acyclic graph.<n>Our results suggest that explicit evidence-graph construction is a promising path toward verifiable data-analytic agents.
  arXiv  Detail & Related papers  (2026-06-15T11:50:56Z)
• Towards Improved Sentence Representations using Token Graphs [41.412173502714225]
  We introduce GLOT, a structure-aware pooling module that reframes pooling as relational learning followed by aggregation.<n>On a diagnostic stress test where 90% of tokens are random distractors, GLOT maintains over 97% accuracy while baseline methods collapse.<n>It is competitive with state-of-the-art techniques on benchmarks like GLUE and MTEB with 20x fewer trainable parameters and speeds up the training time by over 100x compared with parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2026-03-03T09:00:01Z)
• Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs [7.158582263989492]
  We build paired citation graphs, ground truth and GPT-4o-generated (from parametric knowledge) for 10,000 papers from SciSciNet.<n>We show that GPT barely separates from ground truth (RF accuracy $approx$ 0.60) despite cleanly rejecting the random baseline.<n> embeddings sharply increase separability: RF on aggregated embeddings reaches $approx$ 0.83, and GNNs with embedding node features achieve 93% test accuracy on GPT vs. ground truth.
  arXiv  Detail & Related papers  (2026-01-28T15:37:31Z)
• Real-time nonlinear inversion of magnetic resonance elastography with operator learning [0.06797079068199119]
  The oNLI framework enables real-time MRE inversion (30,000x speedup) of elastograms with comparable spatial accuracy to NLI.<n>A structural prior mechanism, analogous to Soft Prior Regularization in the MRE literature, was incorporated to improve spatial accuracy.
  arXiv  Detail & Related papers  (2025-10-03T08:55:40Z)
• RLIPv2: Fast Scaling of Relational Language-Image Pre-training [53.21796397618875]
  We propose RLIPv2, a fast converging model that enables the relational scaling of pre-training to large-scale pseudo-labelled scene graph data. Asymmetric Language-Image Fusion (ALIF) facilitates earlier and deeper gated cross-modal fusion with sparsified language encoding. RLIPv2 shows state-of-the-art performance on three benchmarks under fully-finetuning, few-shot and zero-shot settings.
  arXiv  Detail & Related papers  (2023-08-18T07:17:09Z)
• Validity Assessment of Legal Will Statements as Natural Language Inference [16.292117261545226]
  This work introduces a natural language inference (NLI) dataset that focuses on the validity of statements in legal wills. This dataset is unique because: (a) each entailment decision requires three inputs: the statement from the will, the law, and the conditions that hold at the time of the testator's death; and (b) the included texts are longer than the ones in current NLI datasets.
  arXiv  Detail & Related papers  (2022-10-30T23:53:13Z)
• NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search [55.75621026447599]
  We propose NAS-Bench-Graph, a tailored benchmark that supports unified, reproducible, and efficient evaluations for GraphNAS. Specifically, we construct a unified, expressive yet compact search space, covering 26,206 unique graph neural network (GNN) architectures. Based on our proposed benchmark, the performance of GNN architectures can be directly obtained by a look-up table without any further computation.
  arXiv  Detail & Related papers  (2022-06-18T10:17:15Z)
• Collaborative likelihood-ratio estimation over graphs [55.98760097296213]
  Graph-based Relative Unconstrained Least-squares Importance Fitting (GRULSIF) We develop this idea in a concrete non-parametric method that we call Graph-based Relative Unconstrained Least-squares Importance Fitting (GRULSIF) We derive convergence rates for our collaborative approach that highlights the role played by variables such as the number of available observations per node, the size of the graph, and how accurately the graph structure encodes the similarity between tasks.
  arXiv  Detail & Related papers  (2022-05-28T15:37:03Z)
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning [63.97983530843762]
  Graph Neural Networks (GNNs) have achieved great success in graph representation learning. GNNs generate identical representations for graph substructures that may in fact be very different. More powerful GNNs, proposed recently by mimicking higher-order tests, are inefficient as they cannot sparsity of underlying graph structure. We propose Distance Depiction (DE) as a new class of graph representation learning.
  arXiv  Detail & Related papers  (2020-08-31T23:15:40Z)
• Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs [0.0]
  Graph Convolutional Networks (GCNs) have proven to be successful tools for semi-supervised classification on graph-based datasets. We propose a new GCN variant whose three-part filter space is targeted at dense graphs.
  arXiv  Detail & Related papers  (2020-08-03T08:48:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.