ContextPRM: Leveraging Contextual Coherence for multi-domain Test-Time Scaling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916976266313728 |
|---|---|
| author | Zhang, Haotian Liu, Liu Yu, Baosheng Qiu, Jiayan Xiao, Likang Ren, Yanwei Chen, Quan Liu, Xianglong |
| author_facet | Zhang, Haotian Liu, Liu Yu, Baosheng Qiu, Jiayan Xiao, Likang Ren, Yanwei Chen, Quan Liu, Xianglong |
| contents | Process reward models (PRMs) have demonstrated significant efficacy in enhancing the mathematical reasoning capabilities of large language models (LLMs) by leveraging test-time scaling (TTS). However, while most PRMs exhibit substantial gains in mathematical domains, the scarcity of domain-specific training data and knowledge-based learning patterns limits their generalization ability when faced with other domains. To address this limitation, we shift the learning objective from verifying domain-specific knowledge to modeling domain-agnostic logical flow. Centering on contextual coherence between chain-of-thought (CoT) steps, our approach is realized through a novel data annotation and training framework, which enhances the model's generalization capabilities across diverse domains. For instance, our resulting model, ContextPRM, achieves a notable 6.5% average accuracy improvement over the majority voting baseline via weighted majority voting across nine non-mathematical domains in MMLU-Pro, including law, history, and philosophy, significantly surpassing the 2.2% improvement from VersaPRM and 0.5% gains from other mathematics-focused PRMs, demonstrating consistent performance across both mathematical and non-mathematical domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24460 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ContextPRM: Leveraging Contextual Coherence for multi-domain Test-Time Scaling Zhang, Haotian Liu, Liu Yu, Baosheng Qiu, Jiayan Xiao, Likang Ren, Yanwei Chen, Quan Liu, Xianglong Artificial Intelligence Process reward models (PRMs) have demonstrated significant efficacy in enhancing the mathematical reasoning capabilities of large language models (LLMs) by leveraging test-time scaling (TTS). However, while most PRMs exhibit substantial gains in mathematical domains, the scarcity of domain-specific training data and knowledge-based learning patterns limits their generalization ability when faced with other domains. To address this limitation, we shift the learning objective from verifying domain-specific knowledge to modeling domain-agnostic logical flow. Centering on contextual coherence between chain-of-thought (CoT) steps, our approach is realized through a novel data annotation and training framework, which enhances the model's generalization capabilities across diverse domains. For instance, our resulting model, ContextPRM, achieves a notable 6.5% average accuracy improvement over the majority voting baseline via weighted majority voting across nine non-mathematical domains in MMLU-Pro, including law, history, and philosophy, significantly surpassing the 2.2% improvement from VersaPRM and 0.5% gains from other mathematics-focused PRMs, demonstrating consistent performance across both mathematical and non-mathematical domains. |
| title | ContextPRM: Leveraging Contextual Coherence for multi-domain Test-Time Scaling |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.24460 |