VSE knjižnice (vzajemna bibliografsko-kataložna baza podatkov COBIB.SI)
  • Identifying and decomposing compound ingredients in meal plans using large language models [Elektronski vir]
    Kopitar, Leon ...
    This study explores the effectiveness of Large Language Models in meal planning, focusing on their ability to identify and decompose compound ingredients. We evaluated three models-GPT-4o, Llama-3 ... (70b), and Mixtral (8x7b)-to assess their proficiency in recognizing and breaking down complex ingredient combinations. Preliminary results indicate that while Llama-3 (70b) and GPT-4o excels in accurate decomposition, all models encounter difficulties with identifying essential elements like seasonings and oils. Despite strong overall performance, variations in accuracy and completeness were observed across models. These findings underscore LLMs' potential to enhance personalized nutrition but highlight the need for further refinement in ingredient decomposition. Future research should address these limitations to improve nutritional recommendations and health outcomes.
    Vir: Proceedings of the First International Workshop on Next-Generation Language Models for Knowledge Representation and Reasoning (NeLaMKRR 2024) [Elektronski vir] : November 2-8, 2024, Hanoi, Vietnam (Str. 1-5)
    Vrsta gradiva - prispevek na konferenci ; neleposlovje za odrasle
    Leto - 2024
    Jezik - angleški
    COBISS.SI-ID - 218583299

    Povezava(-e):

    https://arxiv.org/pdf/2411.05892

Vnos na polico