Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912365305397248 |
|---|---|
| author | Zou, Xin Wang, Yizhou Yan, Yibo Lyu, Yuanhuiyi Zheng, Kening Huang, Sirui Chen, Junkai Jiang, Peijie Liu, Jia Tang, Chang Hu, Xuming |
| author_facet | Zou, Xin Wang, Yizhou Yan, Yibo Lyu, Yuanhuiyi Zheng, Kening Huang, Sirui Chen, Junkai Jiang, Peijie Liu, Jia Tang, Chang Hu, Xuming |
| contents | Despite their impressive capabilities, multimodal large language models (MLLMs) are prone to hallucinations, i.e., the generated content that is nonsensical or unfaithful to input sources. Unlike in LLMs, hallucinations in MLLMs often stem from the sensitivity of text decoder to visual tokens, leading to a phenomenon akin to "amnesia" about visual information. To address this issue, we propose MemVR, a novel decoding paradigm inspired by common cognition: when the memory of an image seen the moment before is forgotten, people will look at it again for factual answers. Following this principle, we treat visual tokens as supplementary evidence, re-injecting them into the MLLM through Feed Forward Network (FFN) as "key-value memory" at the middle trigger layer. This "look-twice" mechanism occurs when the model exhibits high uncertainty during inference, effectively enhancing factual alignment. Comprehensive experimental evaluations demonstrate that MemVR significantly mitigates hallucination across various MLLMs and excels in general benchmarks without incurring additional time overhead. The implementation is available from https://github.com/1zhou-Wang/MemVR |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03577 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models Zou, Xin Wang, Yizhou Yan, Yibo Lyu, Yuanhuiyi Zheng, Kening Huang, Sirui Chen, Junkai Jiang, Peijie Liu, Jia Tang, Chang Hu, Xuming Computer Vision and Pattern Recognition Despite their impressive capabilities, multimodal large language models (MLLMs) are prone to hallucinations, i.e., the generated content that is nonsensical or unfaithful to input sources. Unlike in LLMs, hallucinations in MLLMs often stem from the sensitivity of text decoder to visual tokens, leading to a phenomenon akin to "amnesia" about visual information. To address this issue, we propose MemVR, a novel decoding paradigm inspired by common cognition: when the memory of an image seen the moment before is forgotten, people will look at it again for factual answers. Following this principle, we treat visual tokens as supplementary evidence, re-injecting them into the MLLM through Feed Forward Network (FFN) as "key-value memory" at the middle trigger layer. This "look-twice" mechanism occurs when the model exhibits high uncertainty during inference, effectively enhancing factual alignment. Comprehensive experimental evaluations demonstrate that MemVR significantly mitigates hallucination across various MLLMs and excels in general benchmarks without incurring additional time overhead. The implementation is available from https://github.com/1zhou-Wang/MemVR |
| title | Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.03577 |