arXiv 2605.229632026-05-21cs.CLcs.AI

图对齐拓扑作为接地检测的归纳偏置

Graph Alignment Topology as an Inductive Bias for Grounding Detection

Department of Pediatrics, University of Illinois College of Medicine Peoria（伊利诺伊大学皮奥里亚医学院儿科部）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机与数据科学学院）；Carle Illinois College of Medicine, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校卡莱医学院）

Paul Landes, Pranav Herur, Adam Cross, Jimeng Sun

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出利用图对齐拓扑作为归纳偏置，通过构建参考信息与LLM输出之间的对齐二分图并训练图神经网络建模对齐结构，在幻觉检测和问答任务上取得最先进结果。

摘要：

大型语言模型（LLM）被优化以产生分布上合理的延续，而不是明确验证生成的命题是否源自源文档。这种归纳偏置使得泛化成为可能，但它不编码响应是否相对于参考是接地的。这些问题限制了LLM在严格事实正确性至关重要的领域（如临床决策支持）中的使用。现有的幻觉检测方法通过检索增强、自一致性或声明验证来提高事实性，但通常不直接学习对齐拓扑。为了利用对齐拓扑作为归纳偏置，我们在参考信息和LLM输出之间构建对齐二分图，并训练图神经网络（GNN）通过消息传递来建模对齐结构。该方法在四个不同的幻觉和问答数据集上取得了最先进的结果，优于所有比较的方法，包括基础LLM如GPT-4o。

英文摘要：

Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support. Existing hallucination detection approaches improve factuality through retrieval augmentation, self-consistency, or claim verification, but generally do not learn directly over alignment topology. To leverage alignment topology as an inductive bias, we construct aligned bipartite graphs between reference information and LLM outputs and train a graph neural network (GNN) to model alignment structure using message passing. The method achieves state-of-the-art results on four diverse hallucination and question-answering datasets, outperforming all compared methods, including foundational LLMs such as GPT-4o.

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。