Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
Enhancing Question Answering Precision with Optimized Vector Retrieval and Instructions
01 Nov 2024
Abstract
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.
Metrics
10 Record Views
Details
- Title
- Enhancing Question Answering Precision with Optimized Vector Retrieval and Instructions
- Creators
- Lixiao YangMengyang XuWeimao Ke
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Information Science
- Other Identifier
- 991021958115504721