Lune

ACL Findings2026

DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models

Hao Yang, Jin Wang, Xuejie Zhang

Abstract

Human visual reasoning typically follows a coarse-to-fine attention process, starting from global scene understanding and gradually focusing on question-relevant regions. However, multimodal large language models may deviate from this pattern due to attention drift and the underutilization of visual evidence, which can lead to hallucinations. To mitigate these issues, this study proposes a Dual-Indicator Guided Contrastive Alignment (DICA), which tracks two information-theoretic indicators during inference: Visual Attention Entropy (VAE), which reflects the concentration of visual attention, and Output Image Correlation (OIC), which measures the dependence of generated outputs on the visual input. An abnormal increase in VAE or a decrease in OIC corresponds to different failure modes, which trigger targeted contrastive alignment to restore visual grounding. Experimental results across multiple benchmarks demonstrate that DICA consistently outperforms existing approaches and substantially reduces hallucinations, highlighting the effectiveness of indicator-driven intervention in improving multimodal inference reliability. The code is publicly available at https://github.com/BGWH123/DICA/.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
  • Grounding Multimodal Large Language Models to the World cites Visual Instruction Tuning
  • Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
  • Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning cites Visual Instruction Tuning
  • Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on20

  1. Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
  2. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningWenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong et al.NeurIPS 2023 · 4,013 citations
  3. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language ModelsDeyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li et al.ICLR 2024 · 3,079 citations
  4. Grounding Multimodal Large Language Models to the WorldZhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao et al.ICLR 2024 · 1,170 citations
  5. Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction TuningFuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang et al.ICLR 2024 · 476 citations

Related papers

  1. Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination MitigationYebo Wu, Han Jin, Zhijiang Guo, Li LiACL Findings 2026
  2. Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought ModelsJi Ma, Wei Suo, Peng Wang, Yanning ZhangCVPR 2026 · 3 citations
  3. PostAlign: Multimodal Grounding as a Corrective Lens for MLLMsYixuan Wu, Yang Zhang, Jian Wu, Philip Torr et al.ICLR 2026 · 5 citations
  4. DEGAP: Dynamic Entropy-Guided Attention Perturbation for Contrastive Decoding in Large Vision-Language ModelsHyein Seo, Yuna Jeong, Mingyu Kang, Junhyeong Park et al.ICML 2026
  5. Collaboration Wins More: Dual-Modal Collaborative Attention Reinforcement for Mitigating Large Vision Language Models HallucinationJiye Xie, Yifei Gao, Liangliang You, Xiang Xu et al.ACM MM 2025 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines