作者位次 #2/3ACL 2026Findings· Findings of ACL
C hang J uan: A Comprehensive Benchmark for Book-Length C hinese Story Evaluation
Dingyi Yang · Mingshuo Wang · Qin Jin
摘要
Automatic evaluation of book-length stories remains underexplored, particularly for non-English literature. We introduce ChangJuan, the first benchmark for book-length Chinese story evaluation , comprising 300 novels with metadata, human ratings, and large-scale user reviews. To mitigate the subj...