VaccineRAG：提升多模态大语言模型对有害RAG样本的免疫力
VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples
AI总结：
针对RAG中有害检索样本影响大模型性能的问题，提出基于思维链的VaccineRAG数据集与Partial-GRPO方法，提升模型样本判别与复杂思维链学习能力。
摘要：
检索增强生成（Retrieval Augmented Generation，RAG）通过整合检索与生成模块及外部知识，提升大语言模型（LLMs）的响应准确率，在实时查询和视觉问答任务中展现出突出优势。然而，RAG的效果常受限于检索器的精度：许多输入到生成阶段的检索样本要么不相关，要么具有误导性，成为LLMs性能提升的关键瓶颈。为解决这一问题，我们提出VaccineRAG——一个基于思维链（Chain-of-Thought，CoT）的新型检索增强生成数据集。一方面，VaccineRAG采用基准测试，使用正负样本比例各异的数据对模型进行评估，系统地揭示当前LLMs的固有缺陷。另一方面，它通过提示LLMs在生成最终答案前，为每个样本生成明确的思维链（CoT）分析，增强模型的样本判别能力。此外，为提升模型学习长序列复杂CoT内容的能力，我们提出Partial-GRPO方法。通过将LLMs的输出建模为多个组成部分而非单一整体，我们的模型能够对复杂序列做出更合理的偏好选择，从而增强其学习复杂CoT的能力。在VaccineRAG上开展的综合评估与消融实验验证了所提方案的有效性。代码和数据集将于近期公开发布。
英文摘要：
Retrieval Augmented Generation enhances the response accuracy of Large Language Models (LLMs) by integrating retrieval and generation modules with external knowledge, demonstrating particular strength in real-time queries and Visual Question Answering tasks. However, the effectiveness of RAG is frequently hindered by the precision of the retriever: many retrieved samples fed into the generation phase are irrelevant or misleading, posing a critical bottleneck to LLMs' performance. To address this challenge, we introduce VaccineRAG, a novel Chain-of-Thought-based retrieval-augmented generation dataset. On one hand, VaccineRAG employs a benchmark to evaluate models using data with varying positive/negative sample ratios, systematically exposing inherent weaknesses in current LLMs. On the other hand, it enhances models' sample-discrimination capabilities by prompting LLMs to generate explicit Chain-of-Thought (CoT) analysis for each sample before producing final answers. Furthermore, to enhance the model's ability to learn long-sequence complex CoT content, we propose Partial-GRPO. By modeling the outputs of LLMs as multiple components rather than a single whole, our model can make more informed preference selections for complex sequences, thereby enhancing its capacity to learn complex CoT. Comprehensive evaluations and ablation studies on VaccineRAG validate the effectiveness of the proposed scheme. The code and dataset will be publicly released soon.
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。
