Customizable LLM-Powered Chatbot for Behavioral Science Research
Zenon Lamprou, Yashar Moshfeghi
TL;DR
The paper introduces CLPC, a web-based, LLM-powered chatbot engineered as an experimental instrument for behavioral science research. It combines a React frontend with a Python backend to support cross-platform access, precise data linkage via user authentication and experiment codes, and interchangeable LLMs through configurable prompts and models. A central contribution is the extensible logging system and prompt/configuration templates that allow researchers to modify behavior without coding. The work enables rigorous data collection, easy experimentation across multiple models, and potential adaptation to information retrieval and broader chatbot applications in other domains.
Abstract
The rapid advancement of Artificial Intelligence has resulted in the advent of Large Language Models (LLMs) with the capacity to produce text that closely resembles human communication. These models have been seamlessly integrated into diverse applications, enabling interactive and responsive communication across multiple platforms. The potential utility of chatbots transcends these traditional applications, particularly in research contexts, wherein they can offer valuable insights and facilitate the design of innovative experiments. In this study, we present a Customizable LLM-Powered Chatbot (CLPC), a web-based chatbot system designed to assist in behavioral science research. The system is meticulously designed to function as an experimental instrument rather than a conventional chatbot, necessitating users to input a username and experiment code upon access. This setup facilitates precise data cross-referencing, thereby augmenting the integrity and applicability of the data collected for research purposes. It can be easily expanded to accommodate new basic events as needed; and it allows researchers to integrate their own logging events without the necessity of implementing a separate logging mechanism. It is worth noting that our system was built to assist primarily behavioral science research but is not limited to it, it can easily be adapted to assist information retrieval research or interacting with chat bot agents in general.