# Collabs

- URL: https://giubots.net/research/collabs/

This research line groups together all those publications that are the results of collaborations and do not immediately fit into the other main areas of research.

## [Assessing LLMs Responses in the Field of Domestic Sustainability: An Exploratory Study](https://giubots.net/publications/assessing-llms-responses/index.md)

This study evaluates how well large language models can answer questions about domestic sustainability. ChatGPT was found to be the most suitable for integrating into smart home assistants due to its fluency and accessibility, though experts noted its answers sometimes lacked factual accuracy.

## [Delivering Green Persuasion Strategies with a Conversational Agent: a Pilot Study](https://giubots.net/publications/delivering-green-persuasion/index.md)

This pilot study tested a chatbot called Ecobot, designed to promote sustainable energy behaviours using persuasive strategies. Two versions were compared: one using only feedback, and another combining feedback, goal-setting, and social comparison. While both versions were similarly effective in influencing behavior, users preferred the multi-strategy version, reporting stronger engagement and more natural interaction.

## [Child Speech Recognition in Human-Robot Interaction: Problem Solved?](https://giubots.net/publications/child-speech-recognition/index.md)

We revisit a paper on child speech recognition and using the same process, we test the performance of Whisper models. There is still room for improvement but they are perfectly usable. Read here a nice in-depth article on this work.

## [Expressive Furhat: Generating Real-Time Facial Expressions for Human-Robot Dialogue with LLMs](https://giubots.net/publications/expressive-furhat-generating/index.md)

In this paper, we present Expressive Furhat, a system that generates real-time facial expressions for the Furhat robot using large language models based on the dialogue context.