Publication

AI Conversational Agent to solve multilingual administrative questions

View document

Bibliographic Details
Summary:This dissertation presents an AI solution designed to address the challenges faced by temporary employment agencies managing a diverse, multilingual workforce. The study focuses on leveraging an LLM model to enable accurate answers to frequently asked questions in multiple languages. The project objectives include developing and implementing the LLM-Based Con- versational Agent, improving the prompts, and evaluating its performance in providing correct answers to three queries. The results should demonstrate a 95% correctness rate, showcasing the efficacy of streamlining administrative processes. This project contributes to the field of LLM-Based Conversational Agents by offering a practical solution to the language barriers in temporary employment agencies, empha- sizing the potential for improved efficiency and reduced back-office support overhead. The findings underscore the significance of AI-driven solutions in addressing complex administrative challenges in multilingual environments.
Main Authors:Alegria, Rodrigo Daniel Sapateiro
Subject:Artificial Intelligence Administrative Questions Multilingual Chat bot Large Language Model
Year:2024
Country:Portugal
Document type:master thesis
Access type:open access
Associated institution:Universidade Nova de Lisboa
Language:English
Origin:Repositório Institucional da UNL
Description
Summary:This dissertation presents an AI solution designed to address the challenges faced by temporary employment agencies managing a diverse, multilingual workforce. The study focuses on leveraging an LLM model to enable accurate answers to frequently asked questions in multiple languages. The project objectives include developing and implementing the LLM-Based Con- versational Agent, improving the prompts, and evaluating its performance in providing correct answers to three queries. The results should demonstrate a 95% correctness rate, showcasing the efficacy of streamlining administrative processes. This project contributes to the field of LLM-Based Conversational Agents by offering a practical solution to the language barriers in temporary employment agencies, empha- sizing the potential for improved efficiency and reduced back-office support overhead. The findings underscore the significance of AI-driven solutions in addressing complex administrative challenges in multilingual environments.