让低信心推理自动反思纠错，效率不降精度提升
Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction
- 低信心时不停止生成，转而触发自我反思修正推理路径
- 在AIME 2025上比先进早停基线提升准确率，计算成本相当
- 适合追求高精度且对推理过程可解释性有要求的研究者
大型语言模型在复杂推理任务中表现优异，常用链式思考与自一致性等技术。然而，基于集成的方法（如自一致性）常伴随高昂的计算开销。为提升效率，先前工作利用内部置信度信号，通过深度置信等早期停止策略终止低置信轨迹以降低消耗。但该策略会丢弃未完成的推理路径，浪费已有计算。本文提出反射置信机制，将低置信信号从终止指示转变为反思触发器：当置信度低于阈值时，模型不终止生成，而是生成反思提示，分析当前推理状态、识别潜在错误，并沿修正后的路径继续推导。在数学推理基准（包括AIME 2025）上的实验表明，该方法在接近相同计算成本下显著优于先进早停基线，验证了主动自我修正优于被动丢弃的有效性。
原文摘要 · Abstract (English)
Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on multiple reasoning trajectories, often incur substantial computational overhead. To improve efficiency, prior work has leveraged internal confidence signals, where early stopping strategies such as DeepConf reduce cost by terminating low-confidence trajectories. However, this strategy discards incomplete reasoning paths and wastes partial computation. We propose reflective confidence, a novel reasoning framework that transforms low-confidence signals from termination indicators into reflection triggers. When confidence falls below a threshold, instead of stopping generation, the model produces a reflection prompt to analyze the current reasoning state, identify potential errors, and continue generation along a corrected trajectory. Experiments on mathematical reasoning benchmarks, including AIME 2025, demonstrate significant accuracy improvements over advanced early-stopping baselines at comparable computational cost, validating the effectiveness of proactive self-correction over passive discarding.
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。