The simplified information page (SIP) is a simplified discharge summary created to mitigate health risks caused by low medical comprehension. One of the most critical aspects of medical comprehension concerns interpreting medication instructions such as proper dosing, frequency, and duration. In our work, we examine the capacities of mainstream Large Language Models (LLMs) such as ChatGPT and Gemini to generate SIP-like medication-oriented pages based on the provided discharge summaries. We are sharing the initial qualitative assessments of our study based on a small collection of discharge summaries in Serbian, pointing to noticed inaccuracies, unfaithful content, and language quality. Hopefully, these findings might be helpful in addressing the multilingual perspective of patient-oriented language.

In this paper the adequacy of the SETimes corpus as a basis for the comparison of closely related languages that are used in countries that emerged after the breakup of Yugoslavia is discussed by comparing it with other corpora. It is shown that the phenomena observed in this corpus and used to illustrate differences most specifically between Serbian and Croatian are consistent neither with their standards nor with other sources. Thus, results obtained on the basis of the SETimes corpus are corpus-biased and have to be reconsidered. This proves that the size of a corpus and its composition used in a linguistic research are crucial for assessing the obtained results.