通过句子级早期干预缓解对象幻觉
Mitigating Object Hallucinations via Sentence-Level Early Intervention
AI总结：
提出SENTINEL框架，通过句子级早期干预和领域内偏好学习，无需人工标注即可显著减少多模态大语言模型的对象幻觉，并在幻觉和通用能力基准上超越现有方法。
摘要：
多模态大语言模型（MLLMs）彻底改变了跨模态理解，但仍难以应对幻觉——即与视觉输入相矛盾的虚构内容。现有的幻觉缓解方法要么计算成本过高，要么在训练数据和模型输出之间引入分布不匹配。我们识别出一个关键见解：幻觉主要出现在文本生成的早期阶段，并通过后续输出传播。为解决此问题，我们提出了SENTINEL（通过领域内偏好学习的句子级早期干预），一个消除对人工标注依赖的框架。具体来说，我们首先通过迭代采样模型输出、通过与两个开放词汇检测器的交叉验证来验证对象存在性，并将句子分类为幻觉/非幻觉类别，从而引导出高质量的领域内偏好对。随后，我们使用上下文连贯的正样本和幻觉负样本迭代构建上下文感知的偏好数据。最后，我们使用上下文感知偏好损失（C-DPO）训练模型，该损失在幻觉最初显现的句子级别强调判别性学习。实验结果表明，与原始模型相比，SENTINEL可将幻觉减少超过90%，并在幻觉基准和通用能力基准上均优于先前的最先进方法，展示了其优越性和泛化能力。模型、数据集和代码可在 https://github.com/pspdada/SENTINEL 获取。
英文摘要：
Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs. Existing hallucination mitigation methods either incur prohibitive computational costs or introduce distribution mismatches between training data and model outputs. We identify a critical insight: hallucinations predominantly emerge at the early stages of text generation and propagate through subsequent outputs. To address this, we propose SENTINEL (Sentence-level Early iNtervention Through IN-domain prEference Learning), a framework that eliminates dependency on human annotations. Specifically, we first bootstrap high-quality in-domain preference pairs by iteratively sampling model outputs, validating object existence through cross-checking with two open-vocabulary detectors, and classifying sentences into hallucinated/non-hallucinated categories. Subsequently, we use context-coherent positive samples and hallucinated negative samples to build context-aware preference data iteratively. Finally, we train models using a context-aware preference loss (C-DPO) that emphasizes discriminative learning at the sentence level where hallucinations initially manifest. Experimental results show that SENTINEL can reduce hallucinations by over 90% compared to the original model and outperforms the previous state-of-the-art method on both hallucination benchmarks and general capabilities benchmarks, demonstrating its superiority and generalization ability. The models, datasets, and code are available at https://github.com/pspdada/SENTINEL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
