ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs

• URL: http://arxiv.org/abs/2606.31054v1
• Date: Tue, 30 Jun 2026 02:46:10 GMT
• Title: ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs
• Abstract summary: Multimodal Large Language Models (MLLMs) are critically hampered by hallucination.<n>We identify an internal signature of hallucination: progressive degradation of text-to-image cross-attention.<n>We propose ADAPT, an attention-based framework that intervenes directly on text-to-image cross-attention dynamics.
• Score: 32.51643420504522
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) are critically hampered by hallucination, generating content inconsistent with the provided image. In this paper, we identify an internal signature of hallucination: progressive degradation of text-to-image cross-attention during generation, leading to specific failure patterns like unfocused or biased attention. Existing mitigation strategies are largely outcome-driven and do not explicitly target this failure mode. To address this problem, we propose ADAPT (Attention Dynamics Alignment with Preference Tuning), an attention-based framework that intervenes directly on text-to-image cross-attention dynamics. We propose ADAPT with three key contributions: a cross-attention visual anchor refined from early decoding to provide stable spatial grounding, an attention-supervised inference mechanism that detects and corrects attention drift online, and a Visual Attention Guidance DPO that aligns preferences toward visually grounded responses. Experiments show that each component of ADAPT contributes to hallucination reduction, and the full framework achieves new best results across multiple hallucination benchmarks, reducing hallucination rates by 40%-60% across mainstream backbones while preserving general multimodal capabilities. Our work provides an attention-based perspective on mitigating hallucinations by exploring the model's internal text-to-image cross-attention behaviors. Code is available at https://github.com/yao-ustc/ADAPT

Related papers

• See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMs [81.71384150441163]
  We propose Context-aware Attention Intervention (CAI) for large vision-language models (LVLMs)<n>CAI enforces a see only when needed principle via two-axis selectivity: where to look and when to intervene.<n> experiments across multiple LVLM backbones and benchmarks show that CAI achieves state-of-the-art hallucination mitigation.
  arXiv  Detail & Related papers  (2026-06-29T06:35:47Z)
• Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models [65.57985131861399]
  hallucinations are strongly correlated with cognitive bifurcation points that often exhibit high entropy states.<n>We propose V-STAR, a lightweight, holistic training paradigm designed to internalize visually aware reasoning capabilities.
  arXiv  Detail & Related papers  (2026-04-11T13:59:05Z)
• See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment [16.616065291567445]
  Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input.<n>We propose DOP-OBC, a training-free and architecture-agnostic decoding strategy built on the principle of equitable attention.
  arXiv  Detail & Related papers  (2026-04-10T11:01:48Z)
• Focus Matters: Phase-Aware Suppression for Hallucination in Vision-Language Models [8.304027910542446]
  We investigate the internal attention dynamics of vision encoders in Large Vision-Language Models (LVLMs)<n>Our analysis reveals that hallucination behavior is particularly sensitive to tokens receiving low attention during the focus phase.<n>We propose a lightweight inference-time intervention that selectively suppresses such tokens during the focus phase.
  arXiv  Detail & Related papers  (2026-04-04T02:46:58Z)
• SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation [33.381194425912234]
  Large vision-language models (VLMs) frequently suffer from hallucinations, generating content that is inconsistent with visual inputs.<n>We introduce SAGE, a Sink-Aware Grounded Decoding framework that mitigates hallucinations by dynamically modulating self-attention during generation.<n>Our method achieves an average relative improvement of 10.65% on MSCOCO and 7.19% on AMBER across diverse VLM architectures.
  arXiv  Detail & Related papers  (2026-03-29T22:52:03Z)
• Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs [67.69730908817321]
  Internal Positive Attention Dynamics (PAD) in LVLMs naturally reveal semantically core visual regions under the distortions of attention sinks.<n>We propose Positive Attention Dynamics Enhancement (PADE), a training-free attention intervention that constructs a PAD map to identify semantically core visual regions.
  arXiv  Detail & Related papers  (2026-02-17T13:08:06Z)
• Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs [26.144870818163387]
  We propose a framework that models hallucination process via a structural causal graph.<n>We introduce VTACR, a novel metric that quantifies the modality contribution imbalance during decoding.<n>We design a fine-language attention intervention mechanism that dynamically adjusts token- and layer-wise attention.
  arXiv  Detail & Related papers  (2025-11-12T06:13:26Z)
• PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning [87.35309934860938]
  hallucinations in large language models (MLLMs) are strongly associated with insufficient attention allocated to visual tokens.<n>We propose textbfPruneHal, a training-free, simple yet effective method that leverages adaptive KV cache pruning to enhance the model's focus on critical visual information.
  arXiv  Detail & Related papers  (2025-10-22T02:41:07Z)
• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [78.78822033285938]
  Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations.<n>In this work, we introduce REVERSE, a unified framework that integrates hallucination-aware training with on-the-fly self-verification.
  arXiv  Detail & Related papers  (2025-04-17T17:59:22Z)
• Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding [66.06337890279839]
  Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks.<n>LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content.<n>We propose an Inter-Modality Correlation Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner.
  arXiv  Detail & Related papers  (2025-01-03T17:56:28Z)

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.