無監督過程獎勵模型

摘要

過程獎勵模型（PRM）是一種強大的機制，透過提供細粒度的步驟層級監督來引導大型語言模型的推理過程。然而，這種有效性伴隨著顯著的代價：PRM需要每個推理步驟的專家註解，使其成本高昂且難以擴展。在此，我們提出一種訓練無監督PRM（uPRM）的方法，該方法無需任何人工監督，既不需要逐步註解，也不需要最終答案的真實標註驗證。我們方法的關鍵想法是定義一個源自LLM下一個token機率的評分函數，該函數能共同評估一批推理軌跡中第一個錯誤步驟的候選位置。我們在各種場景中展示了uPRM的有效性：（i）在ProcessBench資料集上，uPRM在識別第一個錯誤步驟方面，比以LLM作為裁判的方法達到高達15%的絕對準確率提升；（ii）作為測試時擴展的驗證器，uPRM的表現與有監督的PRM相當，並比多數投票基線高出最多6.9%；（iii）當用作強化學習中的獎勵訊號時，與使用真實標籤訓練的有監督PRM相比，uPRM在整個訓練過程中實現了更穩健的策略最佳化。總體而言，我們的結果為複雜推理任務的可擴展獎勵建模開闢了一條道路。

English

Process Reward Models (PRMs) are a powerful mechanism for steering large language model reasoning by providing fine-grained, step-level supervision. However, this effectiveness comes at a significant cost: PRMs require expert annotations for every reasoning step, making them costly and difficult to scale. Here, we propose a method for training unsupervised PRMs (uPRM) that requires no human supervision, neither at the level of step-by-step annotations nor through ground-truth verification of final answers. The key idea behind our approach is to define a scoring function, derived from LLM next-token probabilities, that jointly assesses candidate positions of first erroneous steps across a batch of reasoning trajectories. We demonstrate the effectiveness of uPRM across diverse scenarios: (i) uPRM achieves up to 15% absolute accuracy improvements over the LLM-as-a-Judge in identifying first erroneous steps on the ProcessBench dataset; (ii) as a verifier for test-time scaling, uPRM performs comparably to supervised PRMs and outperforms the majority voting baseline by up to 6.9%, and (iii) when used as a reward signal in reinforcement learning, uPRM enables more robust policy optimization throughout training compared to a supervised PRM trained using ground-truth labels. Overall, our results open a path toward scalable reward modeling for complex reasoning tasks.