2026-10-08T08:38:56Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33416398 2026-09-30T15:24:33Z category_32942 portal_231 item_type_8 month_year_09_2026

Evaluating Learning Outcomes and Perceptions of LLM-Generated Explanations Across Expertise Levels and Bloom’s Taxonomy Ave Black (24696103) Learning sciences large language models AI in education bloom's taxonomy teaching expertise tacit knowledge LLM-generated <p dir="ltr">This project examines whether the tacit knowledge of large language models (LLMs) can be exploited to improve teaching and learning within the format of educational explanations. This was accomplished by seeing if content and structure of explanations intended to teach a learner were meaningfully changed when prompted to simulate different levels of expertise and whether those differences matter for educational learning objectives. In the first study iteration, we explored how LLMs’ implicit beliefs about teaching expertise change how they explain concepts when prompted to simulate ranging levels of expertise. Using Bloom’s Taxonomy as a framework, I generated explanations across multiple expertise conditions and analyzed them using Linguistic Inquiry and Word Count (LIWC) and qualitative review. The results showed clear differences between expert and novice explanations. We found that expert output appears more analytical and structured, and novice outputs appear more conversational, authentic, and positive in tone. However, the model did not strongly distinguish between finer expert categories, and its explicit predictions about these differences did not fully align with its actual linguistic patterns. Given these findings, we explored whether pedagogical content that exploited the differences in the LLMs emulations of expertise might help or hinder student learning. In an online study of 150 participants, individuals read LLM-generated explanations and completed Bloom-aligned tasks and LIWC aligned evaluation measures. The results showed that expertise level of the explanation mattered differently depending on the learning objective. The novice explanations performed similarly to expert explanations on lower-level Bloom tasks, while expert explanations led to better performance on higher-level Bloom tasks. Additionally, increase in rating for Clout also was shown to improve scores on the learning tasks. The implications for mining LLMs for tacit statistical knowledge and for applications in the educational sector are discussed.</p> 2026-04-17T00:00:00Z Text Thesis 10.1184/R1/33416398.v1 https://figshare.com/articles/thesis/Evaluating_Learning_Outcomes_and_Perceptions_of_LLM-Generated_Explanations_Across_Expertise_Levels_and_Bloom_s_Taxonomy/33416398 CC BY-NC-ND 3.0