Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations

Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang


Abstract
Recently, multimodal large language models (MLLMs) have demonstrated remarkable performance in visual-language tasks. However, the authenticity of the responses generated by MLLMs is often compromised by object hallucinations. We identify that a key cause of these hallucinations is the model’s over-susceptibility to image frequency features in detecting objects. In this paper, we introduce Multi-Frequency Perturbations (MFP), a simple, cost-effective, and pluggable adversarial training method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference, thereby mitigating hallucinations. Experimental results demonstrate that our method significantly mitigates object hallucinations across various model architectures. Furthermore, as a training-time method, MFP can be combined with inference-time methods to achieve state-of-the-art performance on the CHAIR benchmark.
Anthology ID:
2025.findings-emnlp.64
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1230–1247
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.64/
DOI:
Bibkey:
Cite (ACL):
Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, and Xuanjing Huang. 2025. Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 1230–1247, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (Li et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.64.pdf
Checklist:
 2025.findings-emnlp.64.checklist.pdf