CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models

• URL: http://arxiv.org/abs/2604.11087v1
• Date: Mon, 13 Apr 2026 07:09:33 GMT
• Title: CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models
• Abstract summary: We introduce CausalGaze, a novel hallucination detection framework based on structural causal models (SCMs)<n>Experiments demonstrate the effectiveness of CausalGaze, especially achieving over 5.2% improvement in AUROC on the TruthfulQA dataset compared to state-of-the-art baselines.
• Score: 20.20916393164348
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-stakes domains. Existing classification-based methods mainly rely on static and passive signals from internal states, which often captures the noise and spurious correlations, while overlooking the underlying causal mechanisms. To address this limitation, we shift the paradigm from passive observation to active intervention by introducing CausalGaze, a novel hallucination detection framework based on structural causal models (SCMs). CausalGaze models LLMs' internal states as dynamic causal graphs and employs counterfactual interventions to disentangle causal reasoning paths from incidental noise, thereby enhancing model interpretability. Extensive experiments across four datasets and three widely used LLMs demonstrate the effectiveness of CausalGaze, especially achieving over 5.2\% improvement in AUROC on the TruthfulQA dataset compared to state-of-the-art baselines.

Related papers

• CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention [48.20065816234311]
  Vision-Language-Action (VLA) models have driven significant progress in robotic manipulation, yet they struggle with the vision-override phenomenon.<n>We propose CofactVLA, a novel causal intervention framework.<n>We show that CofactVLA establishes a new state-of-the-art across diverse simulation benchmarks.
  arXiv  Detail & Related papers  (2026-08-05T02:58:41Z)
• CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learning [25.21342780360303]
  We propose the Causal-Visual Dynamic Label Refinement framework.<n>It recalibrates visual-semantic associations via a Dual-Stream Mutual Correction Mechanism.<n>Experiments on the CUB, SUN, and AWA2 benchmarks demonstrate that CV-DCLR significantly outperforms state-of-the-art methods in high-ambiguity scenarios.
  arXiv  Detail & Related papers  (2026-07-01T12:45:35Z)
• DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning [48.77865928715759]
  Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models.<n> hallucination remains a critical issue that hinders their reliability.<n>We propose DynHD that bridge these gaps from both spatial (token sequence) and temporal (denoising dynamics) perspectives.
  arXiv  Detail & Related papers  (2026-03-17T12:40:29Z)
• HART: Data-Driven Hallucination Attribution and Evidence-Based Tracing for Large Language Models [4.211691393530721]
  We propose HART, a fine-grained hallucination attribution and evidence retrieval framework for large language models.<n>HART formalizes hallucination tracing as a structured modeling task comprising four stages: span localization, mechanism attribution, evidence retrieval, and causal tracing.<n>Based upon this formulation, we develop the first structured dataset tailored for hallucination tracing.
  arXiv  Detail & Related papers  (2026-03-06T02:23:55Z)
• Scalable Contrastive Causal Discovery under Unknown Soft Interventions [3.165716101116899]
  We propose a scalable causal discovery model for paired observational and interventional settings with shared underlying causal structure and unknown soft interventions.<n> Experiments on synthetic data demonstrate improved causal structure recovery, generalization to unseen graphs with held-out causal mechanisms, and scalability to larger graphs.
  arXiv  Detail & Related papers  (2026-03-03T18:16:16Z)
• CausalMamba: Interpretable State Space Modeling for Temporal Rumor Causality [4.936998293690288]
  CausalMamba is a novel framework that integrates Mamba-based sequence modeling, graph convolutional networks (GCNs), and differentiable causal discovery via NOTEARS.<n>Our framework provides a unified approach for rumor classification and influence analysis, paving the way for more explainable and actionable misinformation detection systems.
  arXiv  Detail & Related papers  (2025-11-20T09:59:16Z)
• Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention [18.08509160653814]
  Large Vision-Language Models (LVLMs) often suffer from object hallucination, making erroneous judgments about the presence of objects in images.<n>We introduce causal analysis into the object recognition scenario of LVLMs, establishing a Structural Causal Model (SCM)<n>We develop Causal-HalBench, a benchmark specifically constructed with counterfactual samples and integrated with comprehensive causal metrics.
  arXiv  Detail & Related papers  (2025-11-13T12:53:03Z)
• 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)
• Spatial Reasoning with Denoising Models [49.83744014336816]
  We introduce a framework to perform reasoning over sets of continuous variables via denoising generative models.<n>For the first time, that order of generation can successfully be predicted by the denoising network itself.<n>Using these findings, we can increase the accuracy of specific reasoning tasks from 1% to >50%.
  arXiv  Detail & Related papers  (2025-02-28T14:08:30Z)
• Quantifying perturbation impacts for large language models [49.1574468325115]
  We introduce Distribution-Based Perturbation Analysis (DBPA), a framework that reformulates perturbation analysis as a frequentist hypothesis testing problem.<n>We demonstrate the effectiveness of DBPA in evaluating perturbation impacts, showing its versatility for perturbation analysis.
  arXiv  Detail & Related papers  (2024-12-01T16:13:09Z)
• Gumbel Counterfactual Generation From Language Models [64.55296662926919]
  We show that counterfactual reasoning is conceptually distinct from interventions.<n>We propose a framework for generating true string counterfactuals.<n>We show that the approach produces meaningful counterfactuals while at the same time showing that commonly used intervention techniques have considerable undesired side effects.
  arXiv  Detail & Related papers  (2024-11-11T17:57:30Z)
• Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning [98.78136504619539]
  Causal Triplet is a causal representation learning benchmark featuring visually more complex scenes. We show that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts.
  arXiv  Detail & Related papers  (2023-01-12T17:43:38Z)
• Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
  Causal mechanisms can be described by structural causal models. One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
  arXiv  Detail & Related papers  (2021-09-06T14:52:58Z)

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.