Grad Detect: Gradient-Based Hallucination Detection in LLMs

• URL: http://arxiv.org/abs/2606.24790v1
• Date: Tue, 23 Jun 2026 16:46:36 GMT
• Title: Grad Detect: Gradient-Based Hallucination Detection in LLMs
• Abstract summary: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations.<n>We present Grad Detect, a gradient-based approach for predicting hallucinations by analyzing layer-wise gradient patterns from a single forward-backward pass during inference.<n>We evaluate Grad Detect on several Q&A benchmarks across both hallucination detection and model abstention prediction, where it consistently outperforms confidence-based and sampling-based baselines.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations. Detecting these hallucinations is critical for deploying LLMs reliably in high-stakes applications. We present Grad Detect, a gradient-based approach for predicting hallucinations by analyzing layer-wise gradient patterns from a single forward-backward pass during inference. Our method shows that the internal gradient structure of a model carries rich information about the correctness of its output. This information is not accessible through output-level signals alone. We evaluate Grad Detect on several Q&A benchmarks across both hallucination detection and model abstention prediction, where it consistently outperforms confidence-based and sampling-based baselines. Through comprehensive layer ablation studies across all eleven models from four architectural families, we find that the final five layers concentrate over 97% of the discriminative gradient signal, enabling efficient deployment with minimal performance loss. Grad Detect provides a unified framework for predicting multiple dimensions of LLM reliability, offering strong predictive performance alongside interpretable insights into where and how model failures originate.

Related papers

• AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models [4.962067184518253]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks.<n>Their tendency to generate hallucinations, namely factually incorrect or unfaithful outputs, poses a critical obstacle to their deployment in high-stakes applications.<n>We propose AURORA, a novel hallucination detection framework that shifts the focus from static representations to the weight-gradient dynamics of LLMs.
  arXiv  Detail & Related papers  (2026-06-28T18:15:00Z)
• A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs [3.4007995136788]
  Layer-contrast decoding, inference-time intervention, and learned logit adapters have demonstrated 10-30 point gains on TruthfulQA.<n>Modern instruction-tuned LLMs already achieve substantially higher baselines.<n> Deliberative prompting methods appear more robust in the evaluated regime.
  arXiv  Detail & Related papers  (2026-06-10T14:48:05Z)
• Scalable Token-Level Hallucination Detection in Large Language Models [63.3426544914783]
  Internal hallucinations are difficult to detect in reasoning-intensive tasks.<n>We propose TokenHD, a holistic pipeline for training token-level hallucination detectors.
  arXiv  Detail & Related papers  (2026-05-12T16:47:40Z)
• Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction [3.6209977238182276]
  Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination.<n>We propose a new method that treats the LLM as a black-box dynamical system.<n>Our method achieves state-of-the-art performance with reduced resource overhead.
  arXiv  Detail & Related papers  (2026-05-06T17:07:29Z)
• Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation [68.41785694664011]
  We propose a plug-and-play framework called Locate-Then-Sparsify for Feature Steering (LTS-FS)<n>It controls the steering intensity according to the hallucination relevance of each layer.<n>Our framework effectively mitigates hallucination while preserving strong performance.
  arXiv  Detail & Related papers  (2026-03-17T09:16:50Z)
• From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis [7.3390265169910665]
  Hallucinations in Large Language Models (LLMs) represent a core obstacle to their reliable deployment in critical domains.<n>To address this limitation, a new research paradigm is proposed, shifting from "detection" to "diagnosis"
  arXiv  Detail & Related papers  (2025-12-31T05:06:35Z)
• Lie to Me: Knowledge Graphs for Robust Hallucination Self-Detection in LLMs [0.0]
  We examine the use of structured knowledge representations, namely knowledge graphs, to improve hallucination self-detection.<n>Our results show that LLMs can better analyse atomic facts when they are structured as knowledge graphs.<n>This low-cost, model-agnostic approach paves the way toward safer and more trustworthy language models.
  arXiv  Detail & Related papers  (2025-12-29T15:41:13Z)
• HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses [0.12499537119440242]
  This paper proposes an explanation enhanced hallucination-detection model, coined as HuDEx.<n>The proposed model provides a novel approach to integrate detection with explanations, and enable both users and the LLM itself to understand and reduce errors.
  arXiv  Detail & Related papers  (2025-02-12T04:17:02Z)
• Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions [60.31496362993982]
  Large language models (LLMs) frequently generate confident yet inaccurate responses.<n>We present a novel, test-time approach to detecting model hallucination through systematic analysis of information flow.
  arXiv  Detail & Related papers  (2024-12-13T16:14:49Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics [51.17512229589]
  PoLLMgraph is a model-based white-box detection and forecasting approach for large language models. We show that hallucination can be effectively detected by analyzing the LLM's internal state transition dynamics. Our work paves a new way for model-based white-box analysis of LLMs, motivating the research community to further explore, understand, and refine the intricate dynamics of LLM behaviors.
  arXiv  Detail & Related papers  (2024-04-06T20:02:20Z)
• A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection [63.56136319976554]
  Large Language Models (LLMs) generate hallucinations, which can cause significant damage when deployed for mission-critical tasks. We propose a self-check approach based on reverse validation to detect factual errors automatically in a zero-resource fashion. We empirically evaluate our method and existing zero-resource detection methods on two datasets.
  arXiv  Detail & Related papers  (2023-10-10T10:14:59Z)

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.