作者位次 #5/12ACL 2026Findings· Findings of ACL
S r D etection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models
Shuaimin Li · Liyang Fan · Zeyang li · Zhuoyue Wan · Yufang Lin · Shiwen Ni · Feiteng Fang · Hamid Alinejad-Rokny · Yuanfeng SONG · Kun Jing · Chen Jason Zhang · Min Yang
摘要
Evaluating code large language models (Code LLMs) requires reliable detection of data leakage, where benchmark performance is artificially inflated by exposure to benchmark data during pre-training. Existing approaches either assume access to proprietary training corpora, rely on brittle heuristi...