LargePiG：你的大型语言模型本质上是一个指针生成器
LargePiG: Your Large Language Model is Secretly a Pointer Generator
AI总结：
提出LargePiG方法，将LLM转为指针生成器以分离内容与形式，有效缓解查询生成中的相关性幻觉和事实性幻觉，提升多场景任务准确率。
摘要：
近期关于查询生成的研究集中在使用大型语言模型（LLMs），这尽管带来了最先进的性能，但也引入了生成查询中的幻觉问题。在这项工作中，我们引入了相关性幻觉和事实性幻觉作为基于LLMs的查询生成带来的幻觉问题的新分类法。我们提出了一种有效的方法来分离LLM生成查询中的内容与形式，该方法保留了从输入中提取和整合的事实知识，并利用LLM强大的语言能力编译句法结构（包括功能词）。具体而言，我们引入了一种与模型无关且无需训练的方法，将大型语言模型转变为指针生成器（LargePiG），其中指针注意力分布利用了LLM固有的注意力权重，而复制概率则源自模型高层与最后一层的词汇分布差异。为验证LargePiG的有效性，我们构建了两个数据集来评估查询生成中的幻觉问题，涵盖文档和视频场景。在各种LLM上的实证研究证明了LargePiG在两个数据集上的优越性。附加实验还验证了LargePiG能够减少大型视觉语言模型中的幻觉，并提高基于文档的问答和事实性评估任务的准确率。
英文摘要：
Recent research on query generation has focused on using Large Language Models (LLMs), which despite bringing state-of-the-art performance, also introduce issues with hallucinations in the generated queries. In this work, we introduce relevance hallucination and factuality hallucination as a new typology for hallucination problems brought by query generation based on LLMs. We propose an effective way to separate content from form in LLM-generated queries, which preserves the factual knowledge extracted and integrated from the inputs and compiles the syntactic structure, including function words, using the powerful linguistic capabilities of the LLM. Specifically, we introduce a model-agnostic and training-free method that turns the Large Language Model into a Pointer-Generator (LargePiG), where the pointer attention distribution leverages the LLM's inherent attention weights, and the copy probability is derived from the difference between the vocabulary distribution of the model's high layers and the last layer. To validate the effectiveness of LargePiG, we constructed two datasets for assessing the hallucination problems in query generation, covering both document and video scenarios. Empirical studies on various LLMs demonstrated the superiority of LargePiG on both datasets. Additional experiments also verified that LargePiG could reduce hallucination in large vision language models and improve the accuracy of document-based question-answering and factuality evaluation tasks.
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。
