Digital Dialogues Under the Microscope: LLM Chatbots vs. Human Interaction

In recent times, Large Language Model (LLM)-driven chatbots have emerged as a focal point in artificial intelligence research. These intelligent systems, leveraging state-of-the-art neural network architectures, represent a significant advancement in natural language processing capabilities. The construction of such chatbots commences with data exploration, where statistical summaries and distribution visualizations are employed to uncover hidden patterns within the dataset. Subsequently, the text undergoes an intensive preprocessing pipeline, including tokenization, stop word removal, and normalization, to ensure data quality for model training. A cutting-edge RoBERTa-based framework is then utilized to generate contextually relevant chatbot responses, followed by fine-tuning to enhance semantic coherence. To assess the authenticity of generated text, a gradient boosting classifier is implemented, trained on a diverse corpus of human and machine-generated utterances. The experimental evaluation reveals that the model attains an accuracy rate of 82%, a precision of 58%, a recall of 60%, and an F1 measure of 0.59. While the high accuracy reflects the model's proficiency in distinguishing between chatbot and human language to a certain extent, the relatively low precision and recall values highlight persistent challenges in accurately classifying text origin. This suggests that there remains room for improvement in refining the model's ability to produce outputs that closely mimic human language while maintaining clear differentiability.