Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912460207816704 |
|---|---|
| author | Zhang, Xiaoyun Ruan, Jingqing Ma, Xing Zhu, Yawen Chen, Jiansong Zeng, Ke Cai, Xunliang |
| author_facet | Zhang, Xiaoyun Ruan, Jingqing Ma, Xing Zhu, Yawen Chen, Jiansong Zeng, Ke Cai, Xunliang |
| contents | Detecting abnormal events in real-world customer service dialogues is highly challenging due to the complexity of business data and the dynamic nature of customer interactions. Moreover, models must demonstrate strong out-of-domain (OOD) generalization to enable rapid adaptation across different business scenarios and maximize commercial value. In this work, we propose a novel Adaptive Perplexity-Aware Reinforcement Learning (APARL) framework that leverages the advanced reasoning capabilities of large language models for abnormal event detection. APARL introduces a dual-loop dynamic curriculum learning architecture, enabling the model to progressively focus on more challenging samples as its proficiency increases. This design effectively addresses performance bottlenecks and significantly enhances OOD transferability. Extensive evaluations on food delivery dialogue tasks show that our model achieves significantly enhanced adaptability and robustness, attaining the highest F1 score with an average improvement of 17.19\%, and an average improvement of 9.59\% in OOD transfer tests. This method provides a superior solution for industrial deployment of anomaly detection models, contributing to improved operational efficiency and commercial benefits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01327 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy Zhang, Xiaoyun Ruan, Jingqing Ma, Xing Zhu, Yawen Chen, Jiansong Zeng, Ke Cai, Xunliang Machine Learning Artificial Intelligence Detecting abnormal events in real-world customer service dialogues is highly challenging due to the complexity of business data and the dynamic nature of customer interactions. Moreover, models must demonstrate strong out-of-domain (OOD) generalization to enable rapid adaptation across different business scenarios and maximize commercial value. In this work, we propose a novel Adaptive Perplexity-Aware Reinforcement Learning (APARL) framework that leverages the advanced reasoning capabilities of large language models for abnormal event detection. APARL introduces a dual-loop dynamic curriculum learning architecture, enabling the model to progressively focus on more challenging samples as its proficiency increases. This design effectively addresses performance bottlenecks and significantly enhances OOD transferability. Extensive evaluations on food delivery dialogue tasks show that our model achieves significantly enhanced adaptability and robustness, attaining the highest F1 score with an average improvement of 17.19\%, and an average improvement of 9.59\% in OOD transfer tests. This method provides a superior solution for industrial deployment of anomaly detection models, contributing to improved operational efficiency and commercial benefits. |
| title | Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.01327 |