Enhancing Question Answering Precision with Optimized Vector Retrieval and Instructions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929575028588544 |
|---|---|
| author | Yang, Lixiao Xu, Mengyang Ke, Weimao |
| author_facet | Yang, Lixiao Xu, Mengyang Ke, Weimao |
| contents | Question-answering (QA) is an important application of Information Retrieval (IR) and language models, and the latest trend is toward pre-trained large neural networks with embedding parameters. Augmenting QA performances with these LLMs requires intensive computational resources for fine-tuning. We propose an innovative approach to improve QA task performances by integrating optimized vector retrievals and instruction methodologies. Based on retrieval augmentation, the process involves document embedding, vector retrieval, and context construction for optimal QA results. We experiment with different combinations of text segmentation techniques and similarity functions, and analyze their impacts on QA performances. Results show that the model with a small chunk size of 100 without any overlap of the chunks achieves the best result and outperforms the models based on semantic segmentation using sentences. We discuss related QA examples and offer insight into how model performances are improved within the two-stage framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01039 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Question Answering Precision with Optimized Vector Retrieval and Instructions Yang, Lixiao Xu, Mengyang Ke, Weimao Information Retrieval Computation and Language Machine Learning Question-answering (QA) is an important application of Information Retrieval (IR) and language models, and the latest trend is toward pre-trained large neural networks with embedding parameters. Augmenting QA performances with these LLMs requires intensive computational resources for fine-tuning. We propose an innovative approach to improve QA task performances by integrating optimized vector retrievals and instruction methodologies. Based on retrieval augmentation, the process involves document embedding, vector retrieval, and context construction for optimal QA results. We experiment with different combinations of text segmentation techniques and similarity functions, and analyze their impacts on QA performances. Results show that the model with a small chunk size of 100 without any overlap of the chunks achieves the best result and outperforms the models based on semantic segmentation using sentences. We discuss related QA examples and offer insight into how model performances are improved within the two-stage framework. |
| title | Enhancing Question Answering Precision with Optimized Vector Retrieval and Instructions |
| topic | Information Retrieval Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2411.01039 |