Question-answering enhancement method for large educational models based on re-ranking and post-retrieval reflection

Computer education is one of the requirements of modern information society education. With the development of large language models, there has been increasing attention on applying of large language models to the computer education process. However, the hallucination problem associated with large l...

Full description

Saved in:
Bibliographic Details
Main Authors: SUN Haoran, WANG Zhihao, WU Yifan, GAO Xiaoying, XIANG Yang
Format: Article
Language:zho
Published: China InfoCom Media Group 2025-01-01
Series:大数据
Subjects:
Online Access:http://www.j-bigdataresearch.com.cn/zh/article/109538360/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849419250120261632
author SUN Haoran
WANG Zhihao
WU Yifan
GAO Xiaoying
XIANG Yang
author_facet SUN Haoran
WANG Zhihao
WU Yifan
GAO Xiaoying
XIANG Yang
author_sort SUN Haoran
collection DOAJ
description Computer education is one of the requirements of modern information society education. With the development of large language models, there has been increasing attention on applying of large language models to the computer education process. However, the hallucination problem associated with large language models poses significant challenges to their application. To solve the challenges, RAG techniques by incorporating external knowledge bases can effectively enhance the quality of responses generated by large language models. However, the traditional RAG techniques lack a fine screening mechanism for the retrieved information, which leads to the retention of a large amount of low-correlation knowledge, and the interference of irrelevant information makes the model hallucination problem not effectively solved. We collected computer-related textbooks and knowledge documents, dividing them into knowledge document blocks according to the content structure to construct an external knowledge database. On this base, we introduced the large educational models question-answering enhancement method based on re-ranking and post-retrieval reflection, which utilized a high-performance multilingual re-ranking model based on a cross-encoder to capture deep semantic information, filter the retrieval information, filter out irrelevant information to improve the retrieval quality. The proposed method applied RAG techniques for model reflection so that the model can further enhance the quality of the model's answers through self-examination, and effectively improve the accuracy of the large language model in computer question-answering. This approach significantly improves the accuracy of large language models in computer question-answering tasks. The proposed method has been tested on several popular current generative models, achieving promising results on CS-Bench, with an approximate 5% increase in accuracy for computer question-answering tasks.
format Article
id doaj-art-00d6a6aea0d54f85b60d22e04ad4edb5
institution Kabale University
issn 2096-0271
language zho
publishDate 2025-01-01
publisher China InfoCom Media Group
record_format Article
series 大数据
spelling doaj-art-00d6a6aea0d54f85b60d22e04ad4edb52025-08-20T03:32:11ZzhoChina InfoCom Media Group大数据2096-02712025-01-01114109538360Question-answering enhancement method for large educational models based on re-ranking and post-retrieval reflectionSUN HaoranWANG ZhihaoWU YifanGAO XiaoyingXIANG YangComputer education is one of the requirements of modern information society education. With the development of large language models, there has been increasing attention on applying of large language models to the computer education process. However, the hallucination problem associated with large language models poses significant challenges to their application. To solve the challenges, RAG techniques by incorporating external knowledge bases can effectively enhance the quality of responses generated by large language models. However, the traditional RAG techniques lack a fine screening mechanism for the retrieved information, which leads to the retention of a large amount of low-correlation knowledge, and the interference of irrelevant information makes the model hallucination problem not effectively solved. We collected computer-related textbooks and knowledge documents, dividing them into knowledge document blocks according to the content structure to construct an external knowledge database. On this base, we introduced the large educational models question-answering enhancement method based on re-ranking and post-retrieval reflection, which utilized a high-performance multilingual re-ranking model based on a cross-encoder to capture deep semantic information, filter the retrieval information, filter out irrelevant information to improve the retrieval quality. The proposed method applied RAG techniques for model reflection so that the model can further enhance the quality of the model's answers through self-examination, and effectively improve the accuracy of the large language model in computer question-answering. This approach significantly improves the accuracy of large language models in computer question-answering tasks. The proposed method has been tested on several popular current generative models, achieving promising results on CS-Bench, with an approximate 5% increase in accuracy for computer question-answering tasks.http://www.j-bigdataresearch.com.cn/zh/article/109538360/large language modelretrieval-augmented generationcomputer education
spellingShingle SUN Haoran
WANG Zhihao
WU Yifan
GAO Xiaoying
XIANG Yang
Question-answering enhancement method for large educational models based on re-ranking and post-retrieval reflection
大数据
large language model
retrieval-augmented generation
computer education
title Question-answering enhancement method for large educational models based on re-ranking and post-retrieval reflection
title_full Question-answering enhancement method for large educational models based on re-ranking and post-retrieval reflection
title_fullStr Question-answering enhancement method for large educational models based on re-ranking and post-retrieval reflection
title_full_unstemmed Question-answering enhancement method for large educational models based on re-ranking and post-retrieval reflection
title_short Question-answering enhancement method for large educational models based on re-ranking and post-retrieval reflection
title_sort question answering enhancement method for large educational models based on re ranking and post retrieval reflection
topic large language model
retrieval-augmented generation
computer education
url http://www.j-bigdataresearch.com.cn/zh/article/109538360/
work_keys_str_mv AT sunhaoran questionansweringenhancementmethodforlargeeducationalmodelsbasedonrerankingandpostretrievalreflection
AT wangzhihao questionansweringenhancementmethodforlargeeducationalmodelsbasedonrerankingandpostretrievalreflection
AT wuyifan questionansweringenhancementmethodforlargeeducationalmodelsbasedonrerankingandpostretrievalreflection
AT gaoxiaoying questionansweringenhancementmethodforlargeeducationalmodelsbasedonrerankingandpostretrievalreflection
AT xiangyang questionansweringenhancementmethodforlargeeducationalmodelsbasedonrerankingandpostretrievalreflection