HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models

• URL: http://arxiv.org/abs/2503.12908v4
• Date: Fri, 23 May 2025 15:32:24 GMT
• Title: HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models
• Authors: Xinyan Jiang, Hang Ye, Yongxin Zhu, Xiaoying Zheng, Zikang Chen, Jun Gong,
• Abstract summary: Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect.<n>We introduce HICD, a novel method designed to induce hallucinations for contrastive decoding to mitigate hallucinations.
• Score: 5.5957864358384795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. We introduce HICD, a novel method designed to induce hallucinations for contrastive decoding to mitigate hallucinations. Unlike existing contrastive decoding methods, HICD selects attention heads crucial to the model's prediction as inducing heads, then induces hallucinations by dispersing attention of these inducing heads and compares the hallucinated outputs with the original outputs to obtain the final result. Our approach significantly improves performance on tasks requiring contextual faithfulness, such as context completion, reading comprehension, and question answering. It also improves factuality in tasks requiring accurate knowledge recall. We demonstrate that our inducing heads selection and attention dispersion method leads to more "contrast-effective" hallucinations for contrastive decoding, outperforming other hallucination-inducing methods. Our findings provide a promising strategy for reducing hallucinations by inducing hallucinations in a controlled manner, enhancing the performance of LLMs in a wide range of tasks.

Related papers

• AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM [28.68190828797428]
  We propose Attention to Generated Text (IAT) to alleviate hallucinations while avoiding repetitive descriptions.<n>AdaIAT employs a layer-wise threshold to control intervention time and fine-grained amplification magnitude tailored to the characteristics of each attention head.
  arXiv  Detail & Related papers  (2026-03-05T07:52:11Z)
• Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance [31.7541034166056]
  Large Vision-Language Models (LVLMs) can reason effectively from image-text inputs and perform well in various multimodal tasks.<n>They are affected by language priors and often produce hallucinations.<n>We propose Residual Decoding (ResDec) to address this problem.
  arXiv  Detail & Related papers  (2026-02-01T06:12:05Z)
• Exploring and Mitigating Fawning Hallucinations in Large Language Models [52.444712272909435]
  We analyze fawning hallucinations in various natural language processing tasks.<n>We tailor the so-termed contrastive decoding method for fawning-hallucination mitigation.
  arXiv  Detail & Related papers  (2025-08-31T14:29:54Z)
• HalluLens: LLM Hallucination Benchmark [49.170128733508335]
  Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as "hallucination" This paper introduces a comprehensive hallucination benchmark, incorporating both new extrinsic and existing intrinsic evaluation tasks.
  arXiv  Detail & Related papers  (2025-04-24T13:40:27Z)
• Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations [82.42811602081692]
  This paper introduces a subsequence association framework to systematically trace and understand hallucinations. Key insight is hallucinations that arise when dominant hallucinatory associations outweigh faithful ones. We propose a tracing algorithm that identifies causal subsequences by analyzing hallucination probabilities across randomized input contexts.
  arXiv  Detail & Related papers  (2025-04-17T06:34:45Z)
• Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models [15.521352228154159]
  multimodal large language models (MLLMs) generate outputs misaligned with obvious visual or factual evidence. We propose a novel framework: Decoupling Contrastive Decoding (DCD) DCD decouples the learning of positive and negative samples in preference datasets, and trains separate positive and negative image projections within the MLLM.
  arXiv  Detail & Related papers  (2025-04-09T02:59:18Z)
• Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer [51.7407540261676]
  We investigate a distinct type of hallucination, where a model can consistently answer a question correctly, but a seemingly trivial perturbation causes it to produce a hallucinated response with high certainty.<n>This phenomenon is particularly concerning in high-stakes domains such as medicine or law, where model certainty is often used as a proxy for reliability.<n>We show that CHOKE examples are consistent across prompts, occur in different models and datasets, and are fundamentally distinct from other hallucinations.
  arXiv  Detail & Related papers  (2025-02-18T15:46:31Z)
• Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence [69.86946427928511]
  We investigate the internal mechanisms driving hallucination in large vision-language models (LVLMs) We introduce Vision-aware Head Divergence (VHD), a metric that quantifies the sensitivity of attention head outputs to visual context. We propose Vision-aware Head Reinforcement (VHR), a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads.
  arXiv  Detail & Related papers  (2024-12-18T15:29:30Z)
• Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models [51.50892380172863]
  We show that most state-of-the-art MLLMs suffer from severe verb hallucination.<n>We propose a novel rich verb knowledge-based tuning method to mitigate verb hallucination.
  arXiv  Detail & Related papers  (2024-12-06T10:53:47Z)
• Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization [123.54980913741828]
  Large Visual Language Models (LVLMs) have demonstrated exceptional abilities in understanding multimodal data. They invariably suffer from hallucinations, leading to a disconnect between the generated text and the corresponding images. Almost all current visual contrastive decoding methods attempt to mitigate these hallucinations by introducing visual uncertainty information. However, they struggle to precisely induce the hallucinatory tokens, which severely limits their effectiveness in mitigating hallucinations.
  arXiv  Detail & Related papers  (2024-05-24T08:46:31Z)
• Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback [40.930238150365795]
  We propose detecting and mitigating hallucinations in Large Vision Language Models (LVLMs) via fine-grained AI feedback.<n>We generate a small-size hallucination annotation dataset by proprietary models.<n>Then, we propose a detect-then-rewrite pipeline to automatically construct preference dataset for training hallucination mitigating model.
  arXiv  Detail & Related papers  (2024-04-22T14:46:10Z)
• Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding [25.489832294197797]
  This paper introduces the Instruction Contrastive Decoding (ICD) method, a novel approach designed to reduce hallucinations during LVLM inference. Our method is inspired by our observation that what we call disturbance instructions significantly exacerbate hallucinations in multimodal fusion modules.
  arXiv  Detail & Related papers  (2024-03-27T16:04:47Z)
• Alleviating Hallucinations of Large Language Models through Induced Hallucinations [67.35512483340837]
  Large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information. We propose a simple textitInduce-then-Contrast Decoding (ICD) strategy to alleviate hallucinations.
  arXiv  Detail & Related papers  (2023-12-25T12:32:49Z)
• HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data [102.56792377624927]
  hallucinations inherent in machine-generated data remain under-explored. We present a novel hallucination detection and elimination framework, HalluciDoctor, based on the cross-checking paradigm. Our method successfully mitigates 44.6% hallucinations relatively and maintains competitive performance compared to LLaVA.
  arXiv  Detail & Related papers  (2023-11-22T04:52:58Z)

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.