Dyve: Thinking Fast and Slow for Dynamic Process Verification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910830993342464 |
|---|---|
| author | Zhong, Jianyuan Li, Zeju Xu, Zhijian Wen, Xiangyu Xu, Qiang |
| author_facet | Zhong, Jianyuan Li, Zeju Xu, Zhijian Wen, Xiangyu Xu, Qiang |
| contents | We present Dyve, a dynamic process verifier that enhances reasoning error detection in large language models by integrating fast and slow thinking, inspired by Kahneman's Systems Theory. Dyve adaptively applies immediate token-level confirmation System 1 for straightforward steps and comprehensive analysis System 2 for complex ones. Leveraging a novel step-wise consensus-filtered process supervision technique, combining Monte Carlo estimation with LLM based evaluation, Dyve curates high-quality supervision signals from noisy data. Experimental results on ProcessBench and the MATH dataset confirm that Dyve significantly outperforms existing process-based verifiers and boosts performance in Best-of-N settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11157 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dyve: Thinking Fast and Slow for Dynamic Process Verification Zhong, Jianyuan Li, Zeju Xu, Zhijian Wen, Xiangyu Xu, Qiang Artificial Intelligence We present Dyve, a dynamic process verifier that enhances reasoning error detection in large language models by integrating fast and slow thinking, inspired by Kahneman's Systems Theory. Dyve adaptively applies immediate token-level confirmation System 1 for straightforward steps and comprehensive analysis System 2 for complex ones. Leveraging a novel step-wise consensus-filtered process supervision technique, combining Monte Carlo estimation with LLM based evaluation, Dyve curates high-quality supervision signals from noisy data. Experimental results on ProcessBench and the MATH dataset confirm that Dyve significantly outperforms existing process-based verifiers and boosts performance in Best-of-N settings. |
| title | Dyve: Thinking Fast and Slow for Dynamic Process Verification |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2502.11157 |