大型语言模型 (LLMs) 表现出了卓越的推理能力。然而，, 通过推理时间缩放来最大化其潜力，面临着采样预算和推理质量之间权衡的挑战。当前的策略仍然效率低下，因为它们通常将采样宽度和深度视为正交目标,，其中宽度共识方法有增强幻觉的风险,，而深度修剪机制过早地截断复杂但有效的推理链。因此,我们提出了双维一致性(DDC),一个统一的框架，将路径质量与自适应终止联系起来。通过将置信加权贝叶斯协议与趋势感知分层修剪,相结合，我们的方法确保计算资源集中在高质量推理路径,上，过滤幻觉，同时加速达成共识。对五个基准的评估表明，这种方法将代币消耗减少了 10 倍以上，同时保持或超过了各个法学硕士的强基线的准确性。
Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling faces challenges in trade-off between sampling budget and reasoning quality. Current strategies remain inefficient as they typically treat sampling width and depth as orthogonal objectives, where width consensus methods risk reinforcing hallucinations, while depth pruning mechanisms prematurely truncate complex yet valid reasoning chains. Therefore, we propose Dual-Dimensional Consistency (DDC), a unified framework that bridges path quality with adaptive termination. By coupling Confidence-Weighted Bayesian protocol with a Trend-Aware Stratified Pruning, our method ensures that computational resources are concentrated on high quality reasoning paths, filtering hallucinations while accelerating consensus. Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)