用单次推理的标记特征，高效估算大模型在表格实体链接中的不确定性。
Efficient Uncertainty Estimation for LLM-based Entity Linking in Tabular Data
- 基于单次输出的标记级特征，自监督估算不确定性
- 准确识别低精度预测结果，计算成本仅为多轮推理的几分之一
- 适合资源受限场景下的实体链接系统部署
将表格数据中的文本值链接到知识库中的对应实体是数据集成与增强的核心任务。尽管大型语言模型（LLMs）在实体链接（EL）任务中表现达到当前最优水平，但其在真实场景中的应用不仅需要高精度预测，还需可靠的不确定性估计，而传统的多轮推理方式计算开销大，严重限制了实际可用性。为此，我们提出一种自监督方法，仅通过单次推理的输出，利用标记级特征估算不确定性，显著降低对多次生成的需求。在多个大型语言模型上针对表格数据的实体链接任务进行评估，结果表明该方法能有效识别低精度输出，同时计算成本仅为传统方法的极小部分，为在基于大模型的实体链接流程中实现低成本、高效率的不确定性估计提供了可行方案。
原文摘要 · Abstract (English)
Linking textual values in tabular data to their corresponding entities in a Knowledge Base is a core task across a variety of data integration and enrichment applications. Although Large Language Models (LLMs) have shown State-of-The-Art performance in Entity Linking (EL) tasks, their deployment in real-world scenarios requires not only accurate predictions but also reliable uncertainty estimates, which require resource-demanding multi-shot inference, posing serious limits to their actual applicability. As a more efficient alternative, we investigate a self-supervised approach for estimating uncertainty from single-shot LLM outputs using token-level features, reducing the need for multiple generations. Evaluation is performed on an EL task on tabular data across multiple LLMs, showing that the resulting uncertainty estimates are highly effective in detecting low-accuracy outputs. This is achieved at a fraction of the computational cost, ultimately supporting a cost-effective integration of uncertainty measures into LLM-based EL workflows. The method offers a practical way to incorporate uncertainty estimation into EL workflows with limited computational overhead.
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。