DEVELOPMENT OF A QUESTION ANSWERING CHATBOT FOR BLOCKCHAIN DOMAIN
Journal Title: Scientific Journal of Astana IT University - Year 2023, Vol 15, Issue 15
Abstract
Large Language Models (LLMs), such as ChatGPT, have transformed the field of natural language processing with their capacity for language comprehension and generation of human-like, fluent responses for many downstream tasks. Despite their impressive capabilities, they often fall short in domain-specific and knowledge-intensive domains due to a lack of access to relevant data. Moreover, most state-of-art LLMs lack transparency as they are often accessible only through APIs. Furthermore, their application in critical real-world scenarios is hindered by their proclivity to produce hallucinated information and inability to leverage external knowledge sources. To address these limitations, we propose an innovative system that enhances LLMs by integrating them with an external knowledge management module. The system allows LLMs to utilize data stored in vector databases, providing them with relevant information for their responses. Additionally, it enables them to retrieve information from the Internet, further broadening their knowledge base. The research approach circumvents the need to retrain LLMs, which can be a resource-intensive process. Instead, it focuses on making more efficient use of existing models. Preliminary results indicate that the system holds promise for improving the performance of LLMs in domain-specific and knowledge-intensive tasks. By equipping LLMs with real-time access to external data, it is possible to harness their language generation capabilities more effectively, without the need to continually strive for larger models.
Authors and Affiliations
Aigerim Mansurova, Aliya Nugumanova, Zhansaya Makhambetova
Keywords
Related Articles
- EP ID EP723057
- DOI -
- Views 48
- Downloads 0
DETERMINATION OF THE MOST POLLUTED ATMOSPHERIC AIR POLLUTION CATEGORY OF ALMATY CITY
This article discusses the impact of suspended particles on human health, by providing small definitions of PM2.5, including how they appear, what particles they consist of, and how they harm the respiratory and circul...
ANALYSIS OF MACHINE LEARNING METHODS FOR PREDICTIONS OF STOCK EXCHANGE SHARE PRICES
Since the stock market is one of the most important areas for investors, stock market price trend prediction is still a hot subject for researchers in both financial and technical fields. Lately, a lot of work has been...
USE OF THE LINK RANKING METHOD TO EVALUATE SCIENTIFIC ACTIVITIES OF SCIENTIFIC SPACE SUBJECTS
A modification of the PageRank method based on link ranking is proposed to evaluate the research results of subjects of the scientific space, taking into account selfcitation. The method of reducing the influence of sel...
SYSTEMATIC DATA PROCUREMENT IN AN OWL-EMBEDDED INFORMATION AND ANALYTICAL FRAMEWORK FOR THE MONITORING OF WATER RESOURCES IN THE ILE-BALKHASH BASIN
The world is facing an escalating water shortage crisis, with dire consequences for ecosystems, human health, and socio-economic development. This article explores the multifaceted nature of the water shortage problem of...
DISTRIBUTION OF ETHEREUM BLOCKCHAIN ADDRESSES
In the contemporary world, Ethereum is a very reliable financial saving among cryptocurrencies. It is also well known as a blockchain platform for creating and launching its own cryptocurrency. The applications run on...