Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning
Ranking
Overall
84
Content
95
Popularity
60
Observed public metrics from 1 member.
Merged summary
TL;DR - ACA-RL trains reasoning models to handle underspecified questions by asking for missing information, giving conditional answers, or abstaining. It improves missing-premise reasoning while retaining competitive performance on well-posed tasks.
- Generates training examples by removing premises from well-posed problems and annotating the resulting gaps.
- Uses structured rewards covering five observable response behaviors.
- Introduces MPB, a 274-instance, human-verified benchmark spanning mathematical, logical, and real-world problems.
- Consistently improves Qwen3 and Llama models on MPB; code, benchmark, and training data are released.
Sources (1)
Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning
Public signals
Hugging Face upvotes 1
TL;DR - ACA-RL trains reasoning models to handle underspecified questions by asking for missing information, giving conditional answers, or abstaining. It improves missing-premise reasoning while retaining competitive performance on well-posed tasks.
- Generates training examples by removing premises from well-posed problems and annotating the resulting gaps.
- Uses structured rewards covering five observable response behaviors.
- Introduces MPB, a 274-instance, human-verified benchmark spanning mathematical, logical, and real-world problems.
- Consistently improves Qwen3 and Llama models on MPB; code, benchmark, and training data are released.