Stereotype or personalization? user identity biases chatbot recommendations

A Kantharuban, J Milbauer, E Strubell… - arxiv preprint arxiv …, 2024 - arxiv.org
We demonstrate that when people use large language models (LLMs) to generate
recommendations, the LLMs produce responses that reflect both what the user wants and …

Implementation and Evaluation of LLM-Based Conversational Systems on a Low-Cost Device

K Sakai, Y Uehara, S Kashihara - 2024 IEEE Global …, 2024 - ieeexplore.ieee.org
The rapid evolution of artificial intelligence (AI) technologies has highlighted the potential of
generative AI, particularly large language models (LLMs), to revolutionize various sectors by …