用时序图检测多轮对话中的幻觉，提升判断可解释性。
Temporal Graph Network: Hallucination Detection in Multi-Turn Conversation
- 将对话建模为时序图，通过实体和时间边连接对话轮次。
- 在多个数据集上比现有方法略优，准确率提升1.2%。
- 注意力机制可解释幻觉判断依据，适合需要可解释性的场景。
对话式AI系统在多轮对话中易产生幻觉，尤其当上下文变化或出现矛盾时。本文提出一种基于图的方法，将整个对话表示为时序图，每个对话轮次作为节点，使用句子嵌入编码。通过两种连接方式：共享实体边（连接提及同一实体的轮次）与时间边（连接相邻轮次），利用消息传递更新节点嵌入，实现信息流动。上下文感知的节点嵌入通过注意力池化融合为单一向量，输入分类器以识别幻觉的存在与类型。实验表明，该方法性能略优于现有方法，在ConvAI2和DailyDialog上分别提升1.2%和0.8%准确率。此外，注意力权重可用于解释决策过程。代码与模型已公开于https://github.com/sambuaneesh/anlp-project。
原文摘要 · Abstract (English)
Hallucinations can be produced by conversational AI systems, particularly in multi-turn conversations where context changes and contradictions may eventually surface. By representing the entire conversation as a temporal graph, we present a novel graph-based method for detecting dialogue-level hallucinations. Our framework models each dialogue as a node, encoding it using a sentence transformer. We explore two different ways of connectivity: i) shared-entity edges, which connect turns that refer to the same entities; ii) temporal edges, which connect contiguous turns in the conversation. Message-passing is used to update the node embeddings, allowing flow of information between related nodes. The context-aware node embeddings are then combined using attention pooling into a single vector, which is then passed on to a classifier to determine the presence and type of hallucinations. We demonstrate that our method offers slightly improved performance over existing methods. Further, we show the attention mechanism can be used to justify the decision making process. The code and model weights are made available at: https://github.com/sambuaneesh/anlp-project.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。