Incorporating Affective Proactive Behavior to a Social Companion Robot for Community Dwelling Older Adults

Villa, Laura; Hervás, Ramón; Dobrescu, Cosmin C.; Cruz-Sandoval, Dagoberto; Favela, Jesús

doi:10.1007/978-3-031-19682-9_72

Cited by 5 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These platforms, being thirdparty systems, provide user-friendly interfaces for the creation, design, and deployment of chatbots, conversational agents, and virtual assistants. They are acclaimed for their comprehensive features, facilitating the construction of interactive and efficient virtual assistants applicable in various sectors, including education [3], healthcare [4,5], early disease detection [6], and addressing recommendations, support queries, and other services [7,8]. Their adaptability and integration capabilities render them favorable options for entities aiming to develop conversational interfaces across diverse channels, industries, and fields.…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Generic and Fine-Tuned Large Language Models for Conversational Agent Systems

Villa,

Carneros-Prado,

Dobrescu

et al. 2024

Robotics

View full text Add to dashboard Cite

In the rapidly evolving domain of conversational agents, the integration of Large Language Models (LLMs) into Chatbot Development Platforms (CDPs) is a significant innovation. This study compares the efficacy of employing generic and fine-tuned GPT-3.5-turbo models for designing dialog flows, focusing on the intent and entity recognition crucial for dynamic conversational interactions. Two distinct approaches are introduced: a generic GPT-based system (G-GPT) leveraging the pre-trained model with complex prompts for intent and entity detection, and a fine-tuned GPT-based system (FT-GPT) employing customized models for enhanced specificity and efficiency. The evaluation encompassed the systems’ ability to accurately classify intents and recognize named entities, contrasting their adaptability, operational efficiency, and customization capabilities. The results revealed that, while the G-GPT system offers ease of deployment and versatility across various contexts, the FT-GPT system demonstrates superior precision, efficiency, and customization, although it requires initial training and dataset preparation. This research highlights the versatility of LLMs in enriching conversational features for talking assistants, from social robots to interactive chatbots. By tailoring these advanced models, the fluidity and responsiveness of conversational agents can be enhanced, making them more adaptable and effective in a variety of settings, from customer service to interactive learning environments.

show abstract