Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective
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_ | 1866912130158034944 |
|---|---|
| author | Zeng, Shenglai Zhang, Jiankun Li, Bingheng Lin, Yuping Zheng, Tianqi Everaert, Dante Lu, Hanqing Liu, Hui Liu, Hui Xing, Yue Cheng, Monica Xiao Tang, Jiliang |
| author_facet | Zeng, Shenglai Zhang, Jiankun Li, Bingheng Lin, Yuping Zheng, Tianqi Everaert, Dante Lu, Hanqing Liu, Hui Liu, Hui Xing, Yue Cheng, Monica Xiao Tang, Jiliang |
| contents | Retrieval-Augmented Generation (RAG) systems have shown promise in enhancing the performance of Large Language Models (LLMs). However, these systems face challenges in effectively integrating external knowledge with the LLM's internal knowledge, often leading to issues with misleading or unhelpful information. This work aims to provide a systematic study on knowledge checking in RAG systems. We conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking. Motivated by the findings, we further develop representation-based classifiers for knowledge filtering. We show substantial improvements in RAG performance, even when dealing with noisy knowledge databases. Our study provides new insights into leveraging LLM representations for enhancing the reliability and effectiveness of RAG systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_14572 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective Zeng, Shenglai Zhang, Jiankun Li, Bingheng Lin, Yuping Zheng, Tianqi Everaert, Dante Lu, Hanqing Liu, Hui Liu, Hui Xing, Yue Cheng, Monica Xiao Tang, Jiliang Machine Learning Computation and Language Retrieval-Augmented Generation (RAG) systems have shown promise in enhancing the performance of Large Language Models (LLMs). However, these systems face challenges in effectively integrating external knowledge with the LLM's internal knowledge, often leading to issues with misleading or unhelpful information. This work aims to provide a systematic study on knowledge checking in RAG systems. We conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking. Motivated by the findings, we further develop representation-based classifiers for knowledge filtering. We show substantial improvements in RAG performance, even when dealing with noisy knowledge databases. Our study provides new insights into leveraging LLM representations for enhancing the reliability and effectiveness of RAG systems. |
| title | Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2411.14572 |