Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916261821153280 |
|---|---|
| author | Liang, Xun Niu, Simin li, Zhiyu Zhang, Sensen Song, Shichao Wang, Hanyu Yang, Jiawei Xiong, Feiyu Tang, Bo Xi, Chenyang |
| author_facet | Liang, Xun Niu, Simin li, Zhiyu Zhang, Sensen Song, Shichao Wang, Hanyu Yang, Jiawei Xiong, Feiyu Tang, Bo Xi, Chenyang |
| contents | Retrieval-Augmented Generation (RAG) offers a cost-effective approach to injecting real-time knowledge into large language models (LLMs). Nevertheless, constructing and validating high-quality knowledge repositories require considerable effort. We propose a pre-retrieval framework named Pseudo-Graph Retrieval-Augmented Generation (PG-RAG), which conceptualizes LLMs as students by providing them with abundant raw reading materials and encouraging them to engage in autonomous reading to record factual information in their own words. The resulting concise, well-organized mental indices are interconnected through common topics or complementary facts to form a pseudo-graph database. During the retrieval phase, PG-RAG mimics the human behavior in flipping through notes, identifying fact paths and subsequently exploring the related contexts. Adhering to the principle of the path taken by many is the best, it integrates highly corroborated fact paths to provide a structured and refined sub-graph assisting LLMs. We validated PG-RAG on three specialized question-answering datasets. In single-document tasks, PG-RAG significantly outperformed the current best baseline, KGP-LLaMA, across all key evaluation metrics, with an average overall performance improvement of 11.6%. Specifically, its BLEU score increased by approximately 14.3%, and the QE-F1 metric improved by 23.7%. In multi-document scenarios, the average metrics of PG-RAG were at least 2.35% higher than the best baseline. Notably, the BLEU score and QE-F1 metric showed stable improvements of around 7.55% and 12.75%, respectively. Our code: https://github.com/IAAR-Shanghai/PGRAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_16933 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning Liang, Xun Niu, Simin li, Zhiyu Zhang, Sensen Song, Shichao Wang, Hanyu Yang, Jiawei Xiong, Feiyu Tang, Bo Xi, Chenyang Computation and Language Information Retrieval Retrieval-Augmented Generation (RAG) offers a cost-effective approach to injecting real-time knowledge into large language models (LLMs). Nevertheless, constructing and validating high-quality knowledge repositories require considerable effort. We propose a pre-retrieval framework named Pseudo-Graph Retrieval-Augmented Generation (PG-RAG), which conceptualizes LLMs as students by providing them with abundant raw reading materials and encouraging them to engage in autonomous reading to record factual information in their own words. The resulting concise, well-organized mental indices are interconnected through common topics or complementary facts to form a pseudo-graph database. During the retrieval phase, PG-RAG mimics the human behavior in flipping through notes, identifying fact paths and subsequently exploring the related contexts. Adhering to the principle of the path taken by many is the best, it integrates highly corroborated fact paths to provide a structured and refined sub-graph assisting LLMs. We validated PG-RAG on three specialized question-answering datasets. In single-document tasks, PG-RAG significantly outperformed the current best baseline, KGP-LLaMA, across all key evaluation metrics, with an average overall performance improvement of 11.6%. Specifically, its BLEU score increased by approximately 14.3%, and the QE-F1 metric improved by 23.7%. In multi-document scenarios, the average metrics of PG-RAG were at least 2.35% higher than the best baseline. Notably, the BLEU score and QE-F1 metric showed stable improvements of around 7.55% and 12.75%, respectively. Our code: https://github.com/IAAR-Shanghai/PGRAG. |
| title | Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2405.16933 |