Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations

• URL: http://arxiv.org/abs/2506.02696v1
• Date: Tue, 03 Jun 2025 09:44:28 GMT
• Title: Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations
• Authors: Jinyuan Luo, Zhen Fang, Yixuan Li, Seongheon Park, Ling Chen,
• Abstract summary: A widely adopted strategy to detect hallucination, known as self-assessment, relies on the model's own output confidence to estimate the factual accuracy of its answers.<n>We propose Sample-Specific Prompting (SSP), a new framework that improves self-assessment by analyzing perturbation sensitivity at intermediate representations.<n>SSP significantly outperforms prior methods across a range of hallucination detection benchmarks.
• Score: 25.18901449626428
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hallucination remains a key obstacle to the reliable deployment of large language models (LLMs) in real-world question answering tasks. A widely adopted strategy to detect hallucination, known as self-assessment, relies on the model's own output confidence to estimate the factual accuracy of its answers. However, this strategy assumes that the model's output distribution closely reflects the true data distribution, which may not always hold in practice. As bias accumulates through the model's layers, the final output can diverge from the underlying reasoning process, making output-level confidence an unreliable signal for hallucination detection. In this work, we propose Sample-Specific Prompting (SSP), a new framework that improves self-assessment by analyzing perturbation sensitivity at intermediate representations. These representations, being less influenced by model bias, offer a more faithful view of the model's latent reasoning process. Specifically, SSP dynamically generates noise prompts for each input and employs a lightweight encoder to amplify the changes in representations caused by the perturbation. A contrastive distance metric is then used to quantify these differences and separate truthful from hallucinated responses. By leveraging the dynamic behavior of intermediate representations under perturbation, SSP enables more reliable self-assessment. Extensive experiments demonstrate that SSP significantly outperforms prior methods across a range of hallucination detection benchmarks.

Related papers

• Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models [0.0]
  We propose Counterfactual Probing, a novel approach for detecting and mitigating hallucinations in large language models.<n>Our method dynamically generates counterfactual statements that appear plausible but contain subtle factual errors, then evaluates the model's sensitivity to these perturbations.
  arXiv  Detail & Related papers  (2025-08-03T17:29:48Z)
• ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs [50.18087419133284]
  hallucination detection methods leveraging hidden states predominantly focus on static and isolated representations.<n>We introduce a novel metric, the ICR Score, which quantifies the contribution of modules to the hidden states' update.<n>We propose a hallucination detection method, the ICR Probe, which captures the cross-layer evolution of hidden states.
  arXiv  Detail & Related papers  (2025-07-22T11:44:26Z)
• Attention Head Embeddings with Trainable Deep Kernels for Hallucination Detection in LLMs [47.18623962083962]
  We present a novel approach for detecting hallucinations in large language models.<n>We find that hallucinated responses exhibit smaller deviations from their prompts compared to grounded responses.<n>We propose a model-intrinsic detection method that uses distributional distances as principled hallucination scores.
  arXiv  Detail & Related papers  (2025-06-11T15:59:15Z)
• Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
  MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
  arXiv  Detail & Related papers  (2025-05-26T14:42:35Z)
• A Unified Virtual Mixture-of-Experts Framework:Enhanced Inference and Hallucination Mitigation in Single-Model System [9.764336669208394]
  Generative models, such as GPT and BERT, have significantly improved performance in tasks like text generation and summarization.<n>However, hallucinations "where models generate non-factual or misleading content" are especially problematic in smaller-scale architectures.<n>We propose a unified Virtual Mixture-of-Experts (MoE) fusion strategy that enhances inference performance and mitigates hallucinations in a single Qwen 1.5 0.5B model.
  arXiv  Detail & Related papers  (2025-04-01T11:38:01Z)
• HalluCounter: Reference-free LLM Hallucination Detection in the Wild! [6.5037356041929675]
  HalluCounter is a reference-free hallucination detection method that utilizes both response-response and query-response consistency and alignment patterns.<n>Our method outperforms state-of-the-art approaches by a significant margin, achieving over 90% average confidence in hallucination detection across datasets.
  arXiv  Detail & Related papers  (2025-03-06T16:59:18Z)
• Spatial Reasoning with Denoising Models [49.83744014336816]
  We introduce a framework to perform reasoning over sets of continuous variables via denoising generative models.<n>We demonstrate for the first time, that order of generation can successfully be predicted by the denoising network itself.
  arXiv  Detail & Related papers  (2025-02-28T14:08:30Z)
• 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)
• Enhancing Hallucination Detection through Noise Injection [9.582929634879932]
  Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations.<n>We show that detection can be improved significantly by taking into account model uncertainty in the Bayesian sense.<n>We propose a very simple and efficient approach that perturbs an appropriate subset of model parameters, or equivalently hidden unit activations, during sampling.
  arXiv  Detail & Related papers  (2025-02-06T06:02:20Z)
• Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework [18.54098084470481]
  We analyze sycophancy across vision-language benchmarks and propose an inference-time mitigation framework.<n>Our framework effectively mitigates sycophancy across all evaluated models, while maintaining performance on neutral prompts.
  arXiv  Detail & Related papers  (2024-08-21T01:03:21Z)
• Debiasing Multimodal Large Language Models [61.6896704217147]
  Large Vision-Language Models (LVLMs) have become indispensable tools in computer vision and natural language processing. Our investigation reveals a noteworthy bias in the generated content, where the output is primarily influenced by the underlying Large Language Models (LLMs) prior to the input image. To rectify these biases and redirect the model's focus toward vision information, we introduce two simple, training-free strategies.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)
• Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures [93.17009514112702]
  Pruning, setting a significant subset of the parameters of a neural network to zero, is one of the most popular methods of model compression. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood.
  arXiv  Detail & Related papers  (2023-04-25T07:42:06Z)
• Learning Disentangled Representations with Latent Variation Predictability [102.4163768995288]
  This paper defines the variation predictability of latent disentangled representations. Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs. We develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations.
  arXiv  Detail & Related papers  (2020-07-25T08:54:26Z)

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.