Graph Alignment Topology as an Inductive Bias for Grounding Detection

• URL: http://arxiv.org/abs/2605.22963v1
• Date: Thu, 21 May 2026 18:49:32 GMT
• Title: Graph Alignment Topology as an Inductive Bias for Grounding Detection
• Abstract summary: Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents.<n>This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference.<n>We leverage alignment topology as an inductive bias and train a graph neural network (GNN) to model alignment structure using message passing.<n>The method achieves state-of-the-art results on four diverse hallucination and question-answering datasets, outperforming all compared methods, including foundational LLMs such as GPT-4o.
• Score: 14.219133766480695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support. Existing hallucination detection approaches improve factuality through retrieval augmentation, self-consistency, or claim verification, but generally do not learn directly over alignment topology. To leverage alignment topology as an inductive bias, we construct aligned bipartite graphs between reference information and LLM outputs and train a graph neural network (GNN) to model alignment structure using message passing. The method achieves state-of-the-art results on four diverse hallucination and question-answering datasets, outperforming all compared methods, including foundational LLMs such as GPT-4o.

Related papers

• 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)
• Constrained Paraphrase Consistency for LLM Hallucination Detection [11.075787335043238]
  Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors.<n>We propose Consistency-Constrained Hallucination Detector (CCHD), which formulates training as a constrained optimization problem.
  arXiv  Detail & Related papers  (2026-06-06T13:14:10Z)
• Emergent Misalignment is Easy, Narrow Misalignment is Hard [10.936985574307736]
  Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned.<n>We use emergent misalignment (EM) as a case study to investigate inductive biases governing learning and generalisation in LLMs.<n>We find a linear representation of the narrow solution also exists, and can be learned by introducing a KL divergence loss.
  arXiv  Detail & Related papers  (2026-02-08T07:50:04Z)
• Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time [60.341117019125214]
  We propose a lightweight and plug-and-play Test-time adaptation framework for correcting Unseen Normal pattErns in graph anomaly detection (GAD)<n>To address semantic confusion, a graph aligner is employed to align the shifted data to the original one at the graph attribute level.<n>Extensive experiments on 10 real-world datasets demonstrate that TUNE significantly enhances the generalizability of pre-trained GAD models to both synthetic and real unseen normal patterns.
  arXiv  Detail & Related papers  (2025-11-10T12:10:05Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [79.75818239774952]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs [60.83579255387347]
  Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models.<n>We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting.
  arXiv  Detail & Related papers  (2025-04-14T10:06:27Z)
• Graph Classification with GNNs: Optimisation, Representation and Inductive Bias [0.6445605125467572]
  We argue that such equivalence ignores the accompanying optimization issues and does not provide a holistic view of the GNN learning process. We prove theoretically that the message-passing layers in the graph, have a tendency to search for either discriminative subgraphs, or a collection of discriminative nodes dispersed across the graph.
  arXiv  Detail & Related papers  (2024-08-17T18:15:44Z)
• LADDER: Language Driven Slice Discovery and Error Rectification [16.146099639239615]
  Current clustering or discrete attribute-based slice discovery methods face key limitations.<n>We proposeladder to address the limitations by: (1) leveraging the flexibility of natural language to address incompleteness; and (2) employing LLM's latent textitdomain knowledge and advanced reasoning to analyze sentences and derive hypotheses directly.<n> Rigorous evaluations show thatladder consistently outperforms existing baselines in discovering and mitigating biases.
  arXiv  Detail & Related papers  (2024-07-31T14:49:35Z)
• Redefining the Shortest Path Problem Formulation of the Linear Non-Gaussian Acyclic Model: Pairwise Likelihood Ratios, Prior Knowledge, and Path Enumeration [1.5178009359320295]
  The paper proposes a threefold enhancement to the LiNGAM-SPP framework.<n>The need for parameter tuning is eliminated by using the pairwise likelihood ratio in lieu of kNN-based mutual information.<n>The incorporation of prior knowledge is then enabled by a node-skipping strategy implemented on the graph representation of all causal orderings.
  arXiv  Detail & Related papers  (2024-04-18T05:59:28Z)
• OrthoReg: Improving Graph-regularized MLPs via Orthogonality Regularization [66.30021126251725]
  Graph Neural Networks (GNNs) are currently dominating in modeling graphstructure data. Graph-regularized networks (GR-MLPs) implicitly inject the graph structure information into model weights, while their performance can hardly match that of GNNs in most tasks. We show that GR-MLPs suffer from dimensional collapse, a phenomenon in which the largest a few eigenvalues dominate the embedding space. We propose OrthoReg, a novel GR-MLP model to mitigate the dimensional collapse issue.
  arXiv  Detail & Related papers  (2023-01-31T21:20:48Z)
• The Manifold Hypothesis for Gradient-Based Explanations [55.01671263121624]
  gradient-based explanation algorithms provide perceptually-aligned explanations. We show that the more a feature attribution is aligned with the tangent space of the data, the more perceptually-aligned it tends to be. We suggest that explanation algorithms should actively strive to align their explanations with the data manifold.
  arXiv  Detail & Related papers  (2022-06-15T08:49:24Z)
• Deep Contrastive Graph Representation via Adaptive Homotopy Learning [76.22904270821778]
  Homotopy model is an excellent tool exploited by diverse research works in the field of machine learning. We propose a novel adaptive homotopy framework (AH) in which the Maclaurin duality is employed. AH can be widely utilized to enhance the homotopy-based algorithm.
  arXiv  Detail & Related papers  (2021-06-17T04:46:04Z)

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.