DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912380617752576 |
|---|---|
| author | Guo, Hanghui Zhu, Jia Di, Shimin Shi, Weijie Chen, Zhangze Xu, Jiajie |
| author_facet | Guo, Hanghui Zhu, Jia Di, Shimin Shi, Weijie Chen, Zhangze Xu, Jiajie |
| contents | Dynamic Retrieval-augmented Generation (RAG) has shown great success in mitigating hallucinations in large language models (LLMs) during generation. However, existing dynamic RAG methods face significant limitations in two key aspects: 1) Lack of an effective mechanism to control retrieval triggers, and 2) Lack of effective scrutiny of retrieval content. To address these limitations, we propose an innovative dynamic RAG method, DioR (Adaptive Cognitive Detection and Contextual Retrieval Optimization), which consists of two main components: adaptive cognitive detection and contextual retrieval optimization, specifically designed to determine when retrieval is needed and what to retrieve for LLMs is useful. Experimental results demonstrate that DioR achieves superior performance on all tasks, demonstrating the effectiveness of our work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10198 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation Guo, Hanghui Zhu, Jia Di, Shimin Shi, Weijie Chen, Zhangze Xu, Jiajie Computation and Language Dynamic Retrieval-augmented Generation (RAG) has shown great success in mitigating hallucinations in large language models (LLMs) during generation. However, existing dynamic RAG methods face significant limitations in two key aspects: 1) Lack of an effective mechanism to control retrieval triggers, and 2) Lack of effective scrutiny of retrieval content. To address these limitations, we propose an innovative dynamic RAG method, DioR (Adaptive Cognitive Detection and Contextual Retrieval Optimization), which consists of two main components: adaptive cognitive detection and contextual retrieval optimization, specifically designed to determine when retrieval is needed and what to retrieve for LLMs is useful. Experimental results demonstrate that DioR achieves superior performance on all tasks, demonstrating the effectiveness of our work. |
| title | DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.10198 |