通过剔除低置信度词提升大模型推理准确率
Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning
- 识别解码中低置信度词并针对性干预
- 在数学推理任务上准确率显著提升，输出长度大幅缩短
- 无需训练，适合希望提升推理可靠性的人
大语言模型推理的测试时扩展通常假设均匀增加计算量可提高正确性。然而先前研究显示，推理不确定性高度集中：少数低置信度词导致大量错误和冗余输出。为此，我们提出「思维减法」（Thinking by Subtraction），一种基于置信度的对比解码方法，通过针对性干预提升推理可靠性。该方法在解码过程中检测低置信度词，以最小占位符替换高置信度词生成对比参考分布，并在低置信度位置减去该分布以优化预测。实验表明，该方法在多个数学推理基准上显著提升准确率，同时大幅减少输出长度，且仅带来极小的键值缓存开销。作为无需训练的方法，它通过精准干预低置信度位置实现可靠推理，避免计算冗余。代码将开源于：https://github.com/bolo-web/CCD。
原文摘要 · Abstract (English)
Recent work on test-time scaling for large language model (LLM) reasoning typically assumes that allocating more inference-time computation uniformly improves correctness. However, prior studies show that reasoning uncertainty is highly localized: a small subset of low-confidence tokens disproportionately contributes to reasoning errors and unnecessary output expansion. Motivated by this observation, we propose Thinking by Subtraction, a confidence-driven contrastive decoding approach that improves reasoning reliability through targeted token-level intervention. Our method, Confidence-Driven Contrastive Decoding, detects low-confidence tokens during decoding and intervenes selectively at these positions. It constructs a contrastive reference by replacing high-confidence tokens with minimal placeholders, and refines predictions by subtracting this reference distribution at low-confidence locations. Experiments show that CCD significantly improves accuracy across mathematical reasoning benchmarks while substantially reducing output length, with minimal KV-cache overhead. As a training-free method, CCD enhances reasoning reliability through targeted low-confidence intervention without computational redundancy. Our code will be made available at: https://github.com/bolo-web/CCD.
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。