IAIman Azimi

Iman Azimi

*This is an algorithmically generated author record based on publicly available information.

Iman Azimi has a total of 4 co-authors. Here are the top co-authors by number of shared publications:

  • Amir M. Rahmani

    School of Nursing and Department of Computer Science, University of California Irvine, Irvine, United States

    2 shared publications
  • Li Wang

    Department of Clinical Research, iHealth Labs, Sunnyvale, United States

    2 shared publications
  • Mohan Qi

    Department of Engineering, iHealth Labs, Sunnyvale, United States

    2 shared publications
  • Youlin Li

    Department of Engineering, iHealth Labs, Sunnyvale, United States

    2 shared publications

Latest Publications

  • Top Cited Papers
    Open Access

    Evaluation of LLMs accuracy and consistency in the registered dietitian exam through prompt engineering and knowledge retrieval

    by Iman Azimi, Mohan Qi, Li Wang, Amir M. Rahmani, Youlin Li

    Large language models (LLMs) are fundamentally transforming human-facing applications in the health and well-being domains: boosting patient engagement, accelerating clinical decision-making, and facilitating medical education. Although state-of-the-art LLMs have shown superior performance in several conversational applications, evaluations within nutrition and diet applications are still insufficient. In this paper, we propose to employ the Registered Dietitian (RD) exam to conduct a standard and comprehensive evaluation of state-of-the-art LLMs, GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro, assessing both accuracy and consistency in nutrition queries. Our evaluation includes 1050 RD exam questions encompassing several nutrition topics and proficiency levels. In addition, for the first time, we examine the impact of Zero-Shot (ZS), Chain of Thought (CoT), Chain of Thought with Self Consistency (CoT-SC), and Retrieval Augmented Prompting (RAP) on both accuracy and consistency of the responses. Our findings revealed that while these LLMs obtained acceptable overall performance, their results varied considerably with different prompts and question domains. GPT-4o with CoT-SC prompting outperformed the other approaches, whereas Gemini 1.5 Pro with ZS recorded the highest consistency. For GPT-4o and Claude 3.5, CoT improved the accuracy, and CoT-SC improved both accuracy and consistency. RAP was particularly effective for GPT-4o to answer Expert level questions. Consequently, choosing the appropriate LLM and prompting technique, tailored to the proficiency level and specific domain, can mitigate errors and potential risks in diet and nutrition chatbots.


  • Open Access

    Accuracy and Consistency of LLMs in the Registered Dietitian Exam: The Impact of Prompt Engineering and Knowledge Retrieval

    by Iman Azimi, Mohan Qi, Li Wang, Amir M. Rahmani, Youlin Li

    Large language models (LLMs) are fundamentally transforming human-facing applications in the health and well-being domains: boosting patient engagement, accelerating clinical decision-making, and facilitating medical education. Although state-of-the-art LLMs have shown superior performance in several conversational applications, evaluations within nutrition and diet applications are still insufficient. In this paper, we propose to employ the Registered Dietitian (RD) exam to conduct a standard and comprehensive evaluation of state-of-the-art LLMs, GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro, assessing both accuracy and consistency in nutrition queries. Our evaluation includes 1050 RD exam questions encompassing several nutrition topics and proficiency levels. In addition, for the first time, we examine the impact of Zero-Shot (ZS), Chain of Thought (CoT), Chain of Thought with Self Consistency (CoT-SC), and Retrieval Augmented Prompting (RAP) on both accuracy and consistency of the responses. Our findings revealed that while these LLMs obtained acceptable overall performance, their results varied considerably with different prompts and question domains. GPT-4o with CoT-SC prompting outperformed the other approaches, whereas Gemini 1.5 Pro with ZS recorded the highest consistency. For GPT-4o and Claude 3.5, CoT improved the accuracy, and CoT-SC improved both accuracy and consistency. RAP was particularly effective for GPT-4o to answer Expert level questions. Consequently, choosing the appropriate LLM and prompting technique, tailored to the proficiency level and specific domain, can mitigate errors and potential risks in diet and nutrition chatbots.