通过双维一致性优化，让大模型推理更省资源且更准确。
Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling
- 联合置信度加权与趋势感知分层剪枝，动态平衡推理深度和宽度。
- 在五个基准上减少超10倍的令牌消耗，同时保持或超越基线精度。
- 适合需要高效推理的大模型部署场景，如实时问答系统。
大型语言模型（LLMs）在推理方面展现出卓越能力，但通过推理时缩放最大化其潜力面临采样预算与推理质量之间的权衡挑战。当前策略效率低下，通常将采样宽度与深度视为独立目标：宽度共识方法可能强化幻觉，而深度剪枝机制则过早终止复杂但有效的推理链。为此，我们提出双维一致性（DDC）框架，将路径质量与自适应终止相统一。通过结合置信度加权贝叶斯协议与趋势感知分层剪枝，该方法确保计算资源集中于高质量推理路径，过滤幻觉并加速共识形成。在五个基准上的评估表明，该方法在保持或超越强基线精度的同时，将令牌消耗减少超过10倍，适用于多种LLM。
原文摘要 · Abstract (English)
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.
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。