提出新方法ASCoT，解决大模型推理后期错误更致命的问题。
Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
- 通过语义剪枝压缩冗余步骤，再用位置影响评分筛选高风险后期步骤。
- 在GSM8K和MATH-500上减少21%–30%的令牌消耗，准确率下降小于1.8%。
- 适合追求高效且可靠推理的模型部署场景，尤其关注后期错误控制。
尽管思维链（CoT）提示增强了大语言模型（LLMs）的推理能力，但保障推理可靠性仍是开放挑战。与普遍认为早期错误最致命的级联失败假说相反，我们发现一种反直觉现象——晚期阶段引入的错误更易导致最终答案被破坏，称为‘后期脆弱性’。为此，我们提出ASCoT（自适应自我修正思维链），在效率与鲁棒性间取得平衡。ASCoT首先进行语义剪枝以压缩冗余步骤，随后利用自适应验证管理器（AVM）根据位置影响得分，优先识别高风险的后期步骤，并仅在必要时触发多视角自我修正引擎（MSCE）。在GSM8K和MATH-500上的实验表明，ASCoT有效重分配计算资源：对LLaMA-3.1-8B而言，令牌使用量减少21%–30%，准确率下降低于1.8%，实现了推理效率与推理保真度之间的更优权衡。
原文摘要 · Abstract (English)
While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge. Contrary to the prevailing cascading failure hypothesis which posits that early errors are most detrimental, we identify a counter-intuitive phenomenon termed \textbf{Late-Stage Fragility}: errors introduced in later reasoning stages are significantly more prone to corrupting final answers. To address this, we introduce ASCoT (Adaptive Self-Correction Chain-of-Thought), a method harmonizing efficiency with robust verification. ASCoT first employs semantic pruning to compress redundant steps, then utilizes an Adaptive Verification Manager (AVM) to prioritize high risk, late-stage steps via a positional impact score, triggering a Multi-Perspective Self-Correction Engine (MSCE) only when necessary. Experiments on GSM8K and MATH-500 demonstrate that ASCoT effectively reallocates computational resources: it reduces token usage by 21\%--30\% for LLaMA-3.1-8B with negligible accuracy drops ($<1.8\%$), achieving a superior trade-off between inference efficiency and reasoning fidelity.
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。