arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.11283cs.CLcs.AI
收藏

基于图上下文知识三元组建模的文本生成零资源幻觉检测

Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling

College of Computer, National University of Defense Technology(国防科技大学计算机学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)

Xinyue Fang, Zhen Huang, Zhiliang Tian, Minghui Fang, Ziyi Pan, Quntian Fang, Zhihua Wen, Hengyue Pan, Dongsheng Li

AI总结:

本文提出基于图的上下文感知(GCA)幻觉检测方法,通过三元组分割、图依赖建模与逆向验证,在零资源下提升文本生成幻觉检测效果,优于所有基线。

摘要:

LLMs获得了卓越的性能,但存在幻觉问题。大多数关于检测幻觉的研究集中在具有简短且具体的正确答案的问题上,这些问题很容易检查其忠实度。对于具有开放式答案的文本生成的幻觉检测更具挑战性。一些研究人员使用外部知识来检测生成文本中的幻觉,但特定场景的外部资源难以获取。最近关于在没有外部资源的情况下检测长文本中幻觉的研究通过在多个采样输出之间进行一致性比较来进行。为了处理长文本,研究人员将长文本分割为多个事实,并单独比较每对事实的一致性。然而,这些方法(1)难以在多个事实之间实现对齐;(2)忽略了多个上下文事实之间的依赖关系。在本文中,我们提出了一种基于图的上下文感知(GCA)幻觉检测方法用于文本生成,该方法对齐知识事实,并在一致性比较中考虑上下文知识三元组之间的依赖关系。具体而言,为了对齐多个事实,我们进行面向三元组的响应分割以提取多个知识三元组。为了建模上下文知识三元组(事实)之间的依赖关系,我们将上下文三元组构建为图,并通过RGCN进行消息传递和聚合来增强三元组的交互。为了避免长文本中知识三元组的遗漏,我们通过重建知识三元组进行基于LLM的逆向验证。实验表明,我们的模型增强了幻觉检测能力,并优于所有基线。

英文摘要:

LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that are easy to check the faithfulness. Hallucination detections for text generation with open-ended answers are more challenging. Some researchers use external knowledge to detect hallucinations in generated texts, but external resources for specific scenarios are hard to access. Recent studies on detecting hallucinations in long text without external resources conduct consistency comparison among multiple sampled outputs. To handle long texts, researchers split long texts into multiple facts and individually compare the consistency of each pairs of facts. However, these methods (1) hardly achieve alignment among multiple facts; (2) overlook dependencies between multiple contextual facts. In this paper, we propose a graph-based context-aware (GCA) hallucination detection for text generations, which aligns knowledge facts and considers the dependencies between contextual knowledge triples in consistency comparison. Particularly, to align multiple facts, we conduct a triple-oriented response segmentation to extract multiple knowledge triples. To model dependencies among contextual knowledge triple (facts), we construct contextual triple into a graph and enhance triples' interactions via message passing and aggregating via RGCN. To avoid the omission of knowledge triples in long text, we conduct a LLM-based reverse verification via reconstructing the knowledge triples. Experiments show that our model enhances hallucination detection and excels all baselines.

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。

↑