Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.14271 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909502884806656 |
|---|---|
| author | Yin, Congrui Wei, Evan Zhang, Zhongxing Zhan, Zaifu |
| author_facet | Yin, Congrui Wei, Evan Zhang, Zhongxing Zhan, Zaifu |
| contents | In the paper, we introduce a paper reading assistant, PaperHelper, a potent tool designed to enhance the capabilities of researchers in efficiently browsing and understanding scientific literature. Utilizing the Retrieval-Augmented Generation (RAG) framework, PaperHelper effectively minimizes hallucinations commonly encountered in large language models (LLMs), optimizing the extraction of accurate, high-quality knowledge. The implementation of advanced technologies such as RAFT and RAG Fusion significantly boosts the performance, accuracy, and reliability of the LLMs-based literature review process. Additionally, PaperHelper features a user-friendly interface that facilitates the batch downloading of documents and uses the Mermaid format to illustrate structural relationships between documents. Experimental results demonstrate that PaperHelper, based on a fine-tuned GPT-4 API, achieves an F1 Score of 60.04, with a latency of only 5.8 seconds, outperforming the basic RAG model by 7\% in F1 Score. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14271 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant Yin, Congrui Wei, Evan Zhang, Zhongxing Zhan, Zaifu Computation and Language In the paper, we introduce a paper reading assistant, PaperHelper, a potent tool designed to enhance the capabilities of researchers in efficiently browsing and understanding scientific literature. Utilizing the Retrieval-Augmented Generation (RAG) framework, PaperHelper effectively minimizes hallucinations commonly encountered in large language models (LLMs), optimizing the extraction of accurate, high-quality knowledge. The implementation of advanced technologies such as RAFT and RAG Fusion significantly boosts the performance, accuracy, and reliability of the LLMs-based literature review process. Additionally, PaperHelper features a user-friendly interface that facilitates the batch downloading of documents and uses the Mermaid format to illustrate structural relationships between documents. Experimental results demonstrate that PaperHelper, based on a fine-tuned GPT-4 API, achieves an F1 Score of 60.04, with a latency of only 5.8 seconds, outperforming the basic RAG model by 7\% in F1 Score. |
| title | PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.14271 |