Preprint
Aug 2026
Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning
ACA-RL supports a new mission for NLP evaluation: measuring whether models can recognize when a task is underdetermined and handle uncertainty, not only whether they can answer fully specified questions.
Yong-Qi Tong, Zhenyu Zhang, Zimou Liu et al.
· 0 citations