STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs

Sungeun An, Swanand Ravindra Kadhe, Shailja Thakur, Chad DeLuca, Hima Patel. STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 39675-39705, Association for Computational Linguistics, 2026. [doi]

References

No references recorded for this publication.

Cited by

No citations of this publication recorded.