arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.08077cs.CL
收藏

Conformal Path Reasoning: 通过路径级校准实现可信的知识图谱问答

Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration

Rutgers University(罗格斯大学);Independent Researcher(独立研究者);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);The University of Sydney(悉尼大学)

Shuhang Lin, Chuhao Zhou, Xiao Lin, Zihan Dong, Kuan Lu, Zhencan Peng, Jie Yin, Dimitris N. Metaxas

AI总结:

提出Conformal Path Reasoning (CPR)框架,通过查询级共形校准和残差共形价值网络(RCVNet)学习判别性路径级非一致性分数,在保证有效覆盖的同时将预测集大小平均减少52%。

摘要:

知识图谱问答(KGQA)提供了基于事实的、可解释的推理,但现有方法通常无法对检索到的答案提供可靠的覆盖保证。虽然共形预测(CP)为生成具有统计保证的预测集提供了原则性框架,但先前的共形KGQA方法存在两个关键缺陷:由于无效校准导致的覆盖保证被违反,以及弱分数判别性导致预测集过大。我们提出Conformal Path Reasoning (CPR),一个基于两个关键创新的新型可信KGQA框架。首先,路径级分数上的查询级共形校准保持可交换性以确保有效的覆盖保证。其次,我们引入残差共形价值网络(RCVNet),这是一个通过PUCT引导探索训练的轻量级模块,用于学习判别性的路径级非一致性分数。大量实验表明,与基准数据集上的共形基线相比,CPR将经验覆盖率平均提高45%,同时将预测集大小平均减少52%,突显了其在知识图谱上进行可靠共形推理的有效性。

英文摘要:

Knowledge Graph Question Answering (KGQA) offers grounded, interpretable reasoning, but existing methods often fail to provide reliable coverage guarantees over retrieved answers. While Conformal Prediction (CP) offers a principled framework for producing prediction sets with statistical guarantees, prior conformal KGQA methods suffer from two critical pitfalls: violated coverage guarantees due to invalid calibration, and weak score discriminability that yields excessively large prediction sets. We propose Conformal Path Reasoning (CPR), a novel trustworthy KGQA framework built on two key innovations. First, query-level conformal calibration over path-level scores preserves exchangeability to ensure valid coverage guarantees. Second, we introduce the Residual Conformal Value Network (RCVNet), a lightweight module trained via PUCT-guided exploration to learn discriminative path-level nonconformity scores. Extensive experiments show that CPR significantly improves the Empirical Coverage Rate by 45% while reducing prediction set size by 52% on average over conformal baselines across benchmark datasets, highlighting its effectiveness for reliable conformal reasoning over knowledge graphs.

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。

↑