BioRAG: A RAG-LLM Framework for Biological Question Reasoning
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_ | 1866914912709640192 |
|---|---|
| author | Wang, Chengrui Long, Qingqing Xiao, Meng Cai, Xunxin Wu, Chengjun Meng, Zhen Wang, Xuezhi Zhou, Yuanchun |
| author_facet | Wang, Chengrui Long, Qingqing Xiao, Meng Cai, Xunxin Wu, Chengjun Meng, Zhen Wang, Xuezhi Zhou, Yuanchun |
| contents | The question-answering system for Life science research, which is characterized by the rapid pace of discovery, evolving insights, and complex interactions among knowledge entities, presents unique challenges in maintaining a comprehensive knowledge warehouse and accurate information retrieval. To address these issues, we introduce BioRAG, a novel Retrieval-Augmented Generation (RAG) with the Large Language Models (LLMs) framework. Our approach starts with parsing, indexing, and segmenting an extensive collection of 22 million scientific papers as the basic knowledge, followed by training a specialized embedding model tailored to this domain. Additionally, we enhance the vector retrieval process by incorporating a domain-specific knowledge hierarchy, which aids in modeling the intricate interrelationships among each query and context. For queries requiring the most current information, BioRAG deconstructs the question and employs an iterative retrieval process incorporated with the search engine for step-by-step reasoning. Rigorous experiments have demonstrated that our model outperforms fine-tuned LLM, LLM with search engines, and other scientific RAG frameworks across multiple life science question-answering tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01107 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BioRAG: A RAG-LLM Framework for Biological Question Reasoning Wang, Chengrui Long, Qingqing Xiao, Meng Cai, Xunxin Wu, Chengjun Meng, Zhen Wang, Xuezhi Zhou, Yuanchun Computation and Language Artificial Intelligence Information Retrieval The question-answering system for Life science research, which is characterized by the rapid pace of discovery, evolving insights, and complex interactions among knowledge entities, presents unique challenges in maintaining a comprehensive knowledge warehouse and accurate information retrieval. To address these issues, we introduce BioRAG, a novel Retrieval-Augmented Generation (RAG) with the Large Language Models (LLMs) framework. Our approach starts with parsing, indexing, and segmenting an extensive collection of 22 million scientific papers as the basic knowledge, followed by training a specialized embedding model tailored to this domain. Additionally, we enhance the vector retrieval process by incorporating a domain-specific knowledge hierarchy, which aids in modeling the intricate interrelationships among each query and context. For queries requiring the most current information, BioRAG deconstructs the question and employs an iterative retrieval process incorporated with the search engine for step-by-step reasoning. Rigorous experiments have demonstrated that our model outperforms fine-tuned LLM, LLM with search engines, and other scientific RAG frameworks across multiple life science question-answering tasks. |
| title | BioRAG: A RAG-LLM Framework for Biological Question Reasoning |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2408.01107 |