一作ACL 2026Findings· Findings of ACL
Pause or Fabricate? Training Language Models for Grounded Reasoning
Yiwen Qiu · Linjuan Wu · Yizhou Liu · Yuchen Yan · Jin Ma · Xu Tan · Yao Hu · Daoxin Zhang · Wenqi Zhang · Weiming Lu · Jun Xiao · Yongliang Shen
摘要
Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are incomplete, producing confident but unreliable conclusions—a failure mode we term ungrounded reasoning. We argue that this issue arises not from...