Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910617994002432 |
|---|---|
| author | Liu, Zheng Wu, Chenyuan Shao, Ninglu Xiao, Shitao Li, Chaozhuo Lian, Defu |
| author_facet | Liu, Zheng Wu, Chenyuan Shao, Ninglu Xiao, Shitao Li, Chaozhuo Lian, Defu |
| contents | The existing Retrieval-Augmented Generation (RAG) systems face significant challenges in terms of cost and effectiveness. On one hand, they need to encode the lengthy retrieved contexts before responding to the input tasks, which imposes substantial computational overhead. On the other hand, directly using generic Large Language Models (LLMs) often leads to sub-optimal answers, while task-specific fine-tuning may compromise the LLMs' general capabilities. To address these challenges, we introduce a novel approach called FlexRAG (Flexible Context Adaptation for RAG). In this approach, the retrieved contexts are compressed into compact embeddings before being encoded by the LLMs. Simultaneously, these compressed embeddings are optimized to enhance downstream RAG performance. A key feature of FlexRAG is its flexibility, which enables effective support for diverse compression ratios and selective preservation of important contexts. Thanks to these technical designs, FlexRAG achieves superior generation quality while significantly reducing running costs. Comprehensive experiments on various question-answering datasets validate our approach as a cost-effective and flexible solution for RAG systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15699 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation Liu, Zheng Wu, Chenyuan Shao, Ninglu Xiao, Shitao Li, Chaozhuo Lian, Defu Computation and Language The existing Retrieval-Augmented Generation (RAG) systems face significant challenges in terms of cost and effectiveness. On one hand, they need to encode the lengthy retrieved contexts before responding to the input tasks, which imposes substantial computational overhead. On the other hand, directly using generic Large Language Models (LLMs) often leads to sub-optimal answers, while task-specific fine-tuning may compromise the LLMs' general capabilities. To address these challenges, we introduce a novel approach called FlexRAG (Flexible Context Adaptation for RAG). In this approach, the retrieved contexts are compressed into compact embeddings before being encoded by the LLMs. Simultaneously, these compressed embeddings are optimized to enhance downstream RAG performance. A key feature of FlexRAG is its flexibility, which enables effective support for diverse compression ratios and selective preservation of important contexts. Thanks to these technical designs, FlexRAG achieves superior generation quality while significantly reducing running costs. Comprehensive experiments on various question-answering datasets validate our approach as a cost-effective and flexible solution for RAG systems. |
| title | Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.15699 |