作者位次 #2/5ACL 2026Findings· Findings of ACL
D eep P rune: Parallel Scaling without Inter-trace Redundancy
Shangqing Tu · Yaxuan Li · Yushi Bai · Lei Hou · Juanzi Li
摘要
Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large language models (LLMs) by generating multiple Chain-of-Thought (CoT) traces simultaneously. However, this approach introduces significant computational inefficiency due to inter-trace redundancy —our an...