RESULTS: One of the key applications of LLMs in HTAs is automating the systematic literature review process. LLMs can rapidly review and extract relevant information from a multitude of studies, saving significant time and resources. Secondly, LLMs can aid in identifying and assessing novel treatment comparators, especially in single-arm trials, by analyzing various data sources. Thirdly, LLMs can assist in synthesizing and analyzing RWE to evaluate the long-term effectiveness and safety of healthcare interventions. LLMs can identify trends, patterns, and safety signals that may not be easily identifiable through traditional methods. Additionally, LLMs can facilitate the conceptualization of health economic models by enabling testing of various model structures and clinical pathways, exploring alternative modeling approaches, and refining the model to accurately represent complexities of the healthcare system. By iteratively refining with the assistance of LLMs, analysts can enhance the model's validity, improve its predictive capabilities, reduce uncertainty, and strengthen its suitability for HTAs, which may be challenging to achieve solely through human intelligence.