一作ACL 2026Findings· Findings of ACL
ST a D : Scaffolded Task Design for Identifying Compositional Skill Gaps in LLM s
Sungeun An · Swanand Ravindra Kadhe · Shailja Thakur · Chad DeLuca · Hima Patel
摘要
Benchmarks are often used as a standard to understand LLM capabilities in different domains. However, aggregate benchmark scores provide limited insight into compositional skill gaps of LLMs and how to improve them. To make these weaknesses visible, we propose Scaffolded Task Design (STaD) framew...