一作ACL 2026Poster· Natural Language Processing
One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement
Yixiao Zhou · Dongzhou Cheng · Zhiliang Wu · Yi Yang · Yu Cheng · Hehe Fan
摘要
Large Language Models (LLMs) often fail to utilize their latent reasoning capabilities due to a distributional mismatch between ambiguous human inquiries and the structured logic required for machine activation. Existing alignment methods either incur prohibitive O(N) costs by fine-tuning each mo...