作者位次 #2/4ACL 2026Findings· Findings of ACL
SEC - F in T ables: Evaluating Large Language Models for Detecting Logical Inconsistencies on Tabular Data
Shuyan Ke · Qiong Wu · Hui Li · Liujuan Cao
摘要
Large language models (LLMs) are increasingly deployed in high-stakes domains reliant on tabular data (e.g., financial reporting), where undetected logical inconsistencies such as mismatched totals and components can lead to critical errors. Yet, the ability of LLMs to identify such inconsistenci...