相信你的模型：分佈引導的置信度校準

摘要

隨著測試時擴展技術的進步，大型推理模型展現出卓越的性能，該技術通過生成多個候選回應並選擇最可靠的答案來提升預測準確性。雖然先前研究分析指出，置信度分數等內部模型信號能部分反映回應正確性，並與準確率存在分佈關聯性，但這類分佈信息尚未被充分運用於指導答案選擇。基於此動機，我們提出DistriVoting方法，在投票過程中將分佈先驗作為置信度之外的輔助信號。具體而言，我們的方法（1）首先使用高斯混合模型將混合置信度分佈分解為正負樣本分量，（2）隨後基於分量中的正負樣本應用拒絕過濾器，以減緩兩類分佈的重疊現象。此外，為從分佈本身進一步緩解重疊問題，我們提出SelfStepConf技術，利用步驟級置信度動態調整推理過程，增強兩類分佈的分離度以提升投票中置信度的可靠性。在16個模型與5個基準測試上的實驗表明，我們的方法顯著優於現有最先進技術。

English

Large Reasoning Models have demonstrated remarkable performance with the advancement of test-time scaling techniques, which enhances prediction accuracy by generating multiple candidate responses and selecting the most reliable answer. While prior work has analyzed that internal model signals like confidence scores can partly indicate response correctness and exhibit a distributional correlation with accuracy, such distributional information has not been fully utilized to guide answer selection. Motivated by this, we propose DistriVoting, which incorporates distributional priors as another signal alongside confidence during voting. Specifically, our method (1) first decomposes the mixed confidence distribution into positive and negative components using Gaussian Mixture Models, (2) then applies a reject filter based on positive/negative samples from them to mitigate overlap between the two distributions. Besides, to further alleviate the overlap from the perspective of distribution itself, we propose SelfStepConf, which uses step-level confidence to dynamically adjust inference process, increasing the separation between the two distributions to improve the reliability of confidences in voting. Experiments across 16 models and 5 benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches.

相信你的模型：分佈引導的置信度校準

Believe Your Model: Distribution-Guided Confidence Calibration

摘要

Support