Md. Shahidul Salim , Sk Imran Hossain , Tanim Jalal , Dhiman Kumer Bose , Mohammad Jahid Ibna Basher
{"title":"LLM based QA chatbot builder: A generative AI-based chatbot builder for question answering","authors":"Md. Shahidul Salim , Sk Imran Hossain , Tanim Jalal , Dhiman Kumer Bose , Mohammad Jahid Ibna Basher","doi":"10.1016/j.softx.2024.102029","DOIUrl":null,"url":null,"abstract":"<div><div>Large language model (LLM) based interactive chatbots have been gaining popularity as a tool to serve organizational information among people. Building such a tool goes through several development phases i.e. (a) Data collection and preprocessing, (b) LLM fine-tuning, testing, and inference, and (c) Chat interface development. To streamline this development process, in this paper, we present the LLM Question–Answer (QA) builder, a web application, which assembles all the steps and makes it easy for technical and non-technical users to develop the LLM QA chatbot. The system allows the instruction fine-tuning of following LLMs: Zepyhr, Mistral, Llama-3, Phi, Flan-T5, and user provided model for organization-specific information retrieval (IR), which can be further enhanced by Retrieval Augmented Generation (RAG) techniques. We have added an automatic web crawling based RAG data scrapper. Also, our system contains a human evaluation feature and RAG metrics for assessing model quality.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102029"},"PeriodicalIF":2.4000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"SoftwareX","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S235271102400400X","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0
Abstract
Large language model (LLM) based interactive chatbots have been gaining popularity as a tool to serve organizational information among people. Building such a tool goes through several development phases i.e. (a) Data collection and preprocessing, (b) LLM fine-tuning, testing, and inference, and (c) Chat interface development. To streamline this development process, in this paper, we present the LLM Question–Answer (QA) builder, a web application, which assembles all the steps and makes it easy for technical and non-technical users to develop the LLM QA chatbot. The system allows the instruction fine-tuning of following LLMs: Zepyhr, Mistral, Llama-3, Phi, Flan-T5, and user provided model for organization-specific information retrieval (IR), which can be further enhanced by Retrieval Augmented Generation (RAG) techniques. We have added an automatic web crawling based RAG data scrapper. Also, our system contains a human evaluation feature and RAG metrics for assessing model quality.
期刊介绍:
SoftwareX aims to acknowledge the impact of software on today''s research practice, and on new scientific discoveries in almost all research domains. SoftwareX also aims to stress the importance of the software developers who are, in part, responsible for this impact. To this end, SoftwareX aims to support publication of research software in such a way that: The software is given a stamp of scientific relevance, and provided with a peer-reviewed recognition of scientific impact; The software developers are given the credits they deserve; The software is citable, allowing traditional metrics of scientific excellence to apply; The academic career paths of software developers are supported rather than hindered; The software is publicly available for inspection, validation, and re-use. Above all, SoftwareX aims to inform researchers about software applications, tools and libraries with a (proven) potential to impact the process of scientific discovery in various domains. The journal is multidisciplinary and accepts submissions from within and across subject domains such as those represented within the broad thematic areas below: Mathematical and Physical Sciences; Environmental Sciences; Medical and Biological Sciences; Humanities, Arts and Social Sciences. Originating from these broad thematic areas, the journal also welcomes submissions of software that works in cross cutting thematic areas, such as citizen science, cybersecurity, digital economy, energy, global resource stewardship, health and wellbeing, etcetera. SoftwareX specifically aims to accept submissions representing domain-independent software that may impact more than one research domain.