评测大模型推理结果的可信度估计，发现越准越不准，越准越不稳。
How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains
- 用6类模型生成34万条推理轨迹，覆盖医疗金融等高风险领域
- 文本编码器最会分辨对错（AUROC 0.672），结构模型最会校准可信度（ECE 0.148）
- 复杂模型不比简单模型强，当前方法难以同时做到又准又稳
大模型推理结果的置信度失准会严重影响其在医疗、金融、法律等高风险领域的可靠性，亟需准确评估其长序列、多步输出的置信度。为此，我们提出推理模型置信度估计基准（RMCB），包含来自六种主流大推理模型（LRMs）的347,496条推理轨迹，覆盖临床、金融、法律、数学及复杂通用推理任务，所有样本均附有正确性标注。基于RMCB，我们对十余种基于表示的方法（涵盖序列、图结构和文本架构）进行了大规模实证评估。核心发现：辨别能力（AUROC）与校准度（ECE）存在持续权衡——文本编码器取得最佳AUROC（0.672），而结构感知模型表现最佳ECE（0.148），无一方法能同时领先。此外，模型架构复杂度提升并未稳定优于简单序列基线，表明仅依赖分块隐藏状态的方法存在性能天花板。本研究为该任务提供迄今最全面的基准，确立严格基线，并揭示当前表示方法范式的局限性。
原文摘要 · Abstract (English)
The miscalibration of Large Reasoning Models (LRMs) undermines their reliability in high-stakes domains, necessitating methods to accurately estimate the confidence of their long-form, multi-step outputs. To address this gap, we introduce the Reasoning Model Confidence estimation Benchmark (RMCB), a public resource of 347,496 reasoning traces from six popular LRMs across different architectural families. The benchmark is constructed from a diverse suite of datasets spanning high-stakes domains, including clinical, financial, legal, and mathematical reasoning, alongside complex general reasoning benchmarks, with correctness annotations provided for all samples. Using RMCB, we conduct a large-scale empirical evaluation of over ten distinct representation-based methods, spanning sequential, graph-based, and text-based architectures. Our central finding is a persistent trade-off between discrimination (AUROC) and calibration (ECE): text-based encoders achieve the best AUROC (0.672), while structurally-aware models yield the best ECE (0.148), with no single method dominating both. Furthermore, we find that increased architectural complexity does not reliably outperform simpler sequential baselines, suggesting a performance ceiling for methods relying solely on chunk-level hidden states. This work provides the most comprehensive benchmark for this task to date, establishing rigorous baselines and demonstrating the limitations of current representation-based paradigms.
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。