Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning
Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for a unique answer. In this setting, the useful response is not always refusal: the model should ask for the missing premise, condition its answer on the unknown quantity, or abstain when no informative conditional response is available. We present \emph{Ask-Condition-Abstain Reinforcement Learning} (ACA-RL), a data-augmented RL framework for this setting. Its reasoning-graph-guided pipeline converts well-posed problems into missing-premise traini
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%Learning Structured Reasoning via Tractable Trajectory Control - Apple Machine Learning Research →
- LinkedLinked via arxiv author · 85%Yongqi Tong →
“Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning”
- LinkedLinked via arxiv author · 85%Zhenyu Zhang →
“Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning”
- LinkedLinked via arxiv author · 85%Zimi Liu →
“Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning”
- LinkedLinked via arxiv author · 85%Kewei Fu →
“Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning”
- LinkedLinked via arxiv author · 85%Mingli Song →
“Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning”
- LinkedLinked via arxiv author · 85%Haofei Zhang →
“Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning”
- LinkedLinked via arxiv author · 85%Junshao Zhang →
“Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning”