无需提示词即可生成深度推理路径，通用问答更准确
GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering
- 两阶段分支法结合斐波那契采样与错误回溯生成推理路径
- 在固定和开放问答任务上均显著提升，开放题准确率提升12.3%
- 用语义聚合替代投票，更适合自由答案场景
思维链推理可提升大模型表现，但需人工设计提示。近期提出的CoT解码可在无提示下生成思维链路径，但仅适用于答案集固定的任务。为此，本文提出通用解码策略GCoT-decoding，扩展至更广泛问答场景。该方法采用两阶段分支机制，结合斐波那契采样与启发式错误回溯生成候选路径；将每条路径拆分为推理段与答案段，精确计算路径置信度；最后通过语义相似性聚合路径，识别共识答案，取代传统多数投票。在六个涵盖固定与自由问答的任务上进行大量实验，结果表明，该方法不仅在固定问答任务上保持强性能，且在自由问答任务上实现显著提升，验证了其通用性。
原文摘要 · Abstract (English)
Chain-of-Thought reasoning can enhance large language models, but it requires manually designed prompts to guide the model. Recently proposed CoT-decoding enables the model to generate CoT-style reasoning paths without prompts, but it is only applicable to problems with fixed answer sets. To address this limitation, we propose a general decoding strategy GCoT-decoding that extends applicability to a broader range of question-answering tasks. GCoT-decoding employs a two-stage branching method combining Fibonacci sampling and heuristic error backtracking to generate candidate decoding paths. It then splits each path into a reasoning span and an answer span to accurately compute path confidence, and finally aggregates semantically similar paths to identify a consensus answer, replacing traditional majority voting. We conduct extensive experiments on six datasets covering both fixed and free QA tasks. Our method not only maintains strong performance on fixed QA but also achieves significant improvements on free QA, demonstrating its generality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。