Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929751471423488 |
|---|---|
| author | Jin, Zhao Jin, Lu Luo, Yizhe Feng, Shuo Shi, Yucheng Zheng, Kai Yu, Xinde Xu, Mingliang |
| author_facet | Jin, Zhao Jin, Lu Luo, Yizhe Feng, Shuo Shi, Yucheng Zheng, Kai Yu, Xinde Xu, Mingliang |
| contents | Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design. We propose correctness learning (CL) to enhance human-AI collaboration integrating deductive verification methods and insights from historical high-quality schemes. The typical pattern hidden in historical high-quality schemes, such as change of task priorities in shared resources, provides critical guidance for intelligent agents in learning and decision-making. By utilizing deductive verification methods, we proposed patten-driven correctness learning (PDCL), formally modeling and reasoning the adaptive behaviors-or 'correctness pattern'-of system agents based on historical high-quality schemes, capturing the logical relationships embedded within these schemes. Using this logical information as guidance, we establish a correctness judgment and feedback mechanism to steer the intelligent decision model toward the 'correctness pattern' reflected in historical high-quality schemes. Extensive experiments across multiple working conditions and core parameters validate the framework's components and demonstrate its effectiveness in improving decision-making and resource optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07096 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration Jin, Zhao Jin, Lu Luo, Yizhe Feng, Shuo Shi, Yucheng Zheng, Kai Yu, Xinde Xu, Mingliang Artificial Intelligence Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design. We propose correctness learning (CL) to enhance human-AI collaboration integrating deductive verification methods and insights from historical high-quality schemes. The typical pattern hidden in historical high-quality schemes, such as change of task priorities in shared resources, provides critical guidance for intelligent agents in learning and decision-making. By utilizing deductive verification methods, we proposed patten-driven correctness learning (PDCL), formally modeling and reasoning the adaptive behaviors-or 'correctness pattern'-of system agents based on historical high-quality schemes, capturing the logical relationships embedded within these schemes. Using this logical information as guidance, we establish a correctness judgment and feedback mechanism to steer the intelligent decision model toward the 'correctness pattern' reflected in historical high-quality schemes. Extensive experiments across multiple working conditions and core parameters validate the framework's components and demonstrate its effectiveness in improving decision-making and resource optimization. |
| title | Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.07096 |