面向高效测试时推理的陈述级可靠性评估

摘要

我们提出将“声明级证伪”作为测试时扩展的原则，并通过“声明级可靠性评估”（CLR）加以实现。CLR是一种无需训练的框架，将测试时计算从额外的解决方案采样重新分配给有针对性的验证。由于对整个推理轨迹的评估常常因常规词元的信号稀释而掩盖关键错误，CLR将每条推理轨迹压缩为一组紧凑的、对决策至关重要的声明，从而分离出其逻辑锚点。此外，鉴于在固定模型能力下生成完全正确的解决方案存在固有困难，CLR将重点转向语义证伪。该方法利用了解决方案构建与声明反驳之间的根本不对称性：构建有效的解决方案需要一条无懈可击的推理路径，而反驳一条错误的声明则只需识别出一个决定性的缺陷。这种针对负面证据的定向搜索系统地压缩了高置信度错误轨迹的生存空间，并通过非线性可靠性评分有效抑制了错误共识。在匹配预算条件下，跨四个大语言模型和四个推理基准，CLR通常在pass@1和自洽性上均有所提升。例如，在GPT-OSS-20B/CMIMC25上，CLR比pass@1高出27.15个百分点，并将自洽性准确率从77.50%提升至82.19%，同时词元消耗减少了37.0%。

English

We propose claim-level falsification as a principle for test-time scaling and instantiate it through Claim-Level Reliability Assessment (CLR), a training-free framework that reallocates test-time compute from additional solution sampling to targeted verification. Since whole-trace evaluation often obscures decisive errors due to signal dilution from routine tokens, CLR condenses each reasoning trace into a compact set of decision-critical claims, thereby isolating its logical anchors. Furthermore, recognizing the inherent difficulty of generating entirely correct solutions under fixed model capabilities, CLR shifts the focus to semantic falsification. This approach exploits a fundamental asymmetry between solution construction and claim refutation. Constructing a valid solution requires a flawless reasoning path, whereas refuting an incorrect claim requires identifying only a single decisive flaw. This targeted search for negative evidence systematically compresses the survival space of high-confidence incorrect traces, effectively suppressing erroneous consensus via nonlinear reliability scoring. Across four LLMs and four reasoning benchmarks under matched budgets, CLR generally improves upon pass@1 and self-consistency. On GPT-OSS-20B/CMIMC25, for instance, CLR exceeds pass@1 by 27.15 percentage-points and raises self-consistency accuracy from 77.50\% to 82.19\% with 37.0\% fewer tokens.