Ai2's XYBench Wins EMNLP Best Resource Paper

Ai2 and collaborators released XYBench, winning EMNLP's best resource paper award; it shows five major LLMs struggle to correct users' misguided XY problems even when the true goal is stated.

2026-11-14 ~ 2026-11-14 · 3 related posts

• Ai2's XYBench Wins EMNLP Best Resource Award, Exposing LLMs' XY Problem Blind Spot — allen_ai · 2026-11-14
• Ai2's XYBench Finds Five Top LLMs Fail to Correct Users' Misguided Questions — allen_ai · 2026-11-14
• Ai2 Asks Whether Prompting or Training Can Make LLMs Give More Useful Advice — allen_ai · 2026-11-14