作者位次 #4/5ACL 2026Findings· Findings of ACL
Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say “ I Don’t Know”
Dhruv Madhwal · Lyuxin David Zhang · Dan Roth · Tomer Wolfson · Vivek Gupta
摘要
Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on reliability. We evaluate three task-equivalent prompting...