SOLO taxonomy

Large language models (LLMs) are increasingly used in dental education, but research has focused mainly on answer accuracy. Whether LLMs can identify the cognitive demand of examination items remains unclear. This study evaluated LLM classification fidelity for endodontic multiple-choice questions (MCQs) across three educational taxonomies and compared four publicly accessible models. Two hundred endodontic MCQs from the Turkish Dentistry Specialty Examination (DUS, 2012–2025) were classified by ChatGPT, Gemini, Kimi, and DeepSeek according to Revised Bloom’s Taxonomy, the SOLO Taxonomy, and Miller’s Pyramid. A three-layer expert consensus procedure comprising calibration training, procedural audit, and structured joint deliberation established the expert consensus reference standard. Agreement was assessed using weighted Cohen’s kappa (κw) with bootstrap 95% confidence intervals; classification performance was evaluated using accuracy and macro-averaged F1. Inter-model differences in item-level accuracy were tested using Cochran’s Q with Kendall’s W, followed by Holm–Bonferroni-corrected pairwise McNemar tests. For Revised Bloom’s Taxonomy, Gemini (κw=0.676) and DeepSeek (κw=0.667) achieved substantial agreement, while Kimi (κw=0.428) and ChatGPT (κw=0.365) performed lower. For SOLO, Gemini achieved substantial agreement (κw=0.622), while the remaining models showed moderate agreement. For Miller’s Pyramid, agreement did not exceed fair, with ChatGPT highest (κw=0.372). Inter-model differences were significant for all three taxonomies (all p<0.001). ChatGPT ranked lowest for Revised Bloom and SOLO but highest for Miller. Revised Bloom levels of expert consensus reference standard increased significantly across examination years (Spearman ρ=0.301, p<0.001). LLMs showed meaningful classification fidelity for Revised Bloom and SOLO taxonomies, particularly Gemini and DeepSeek, but performance for Miller’s Pyramid remained weak. Bloom, SOLO, and Miller should not be treated as interchangeable frameworks, and LLM selection should be tailored to the taxonomy and assessment purpose. Answer accuracy and taxonomy classification fidelity represent distinct capabilities that warrant independent evaluation.

Reading is one of the main ways through which middle school students learn English, and the quality of their reading depends largely on the level of thinking involved in the learning process. In actual teaching, however, many reading tasks remain at a low cognitive level, and students encounter difficulty when questions require inference, evaluation, or creation. SOLO taxonomy, which describes the structural complexity of observable learning outcomes, provides a basis for planning and assessing reading tasks across cognitive levels. Drawing on representative studies from China and abroad, this paper reviews research on the application of SOLO taxonomy in English reading teaching in middle schools. It traces the origin and development of the taxonomy, analyzes its compatibility with reading teaching, and examines two lines of applied research, namely SOLO-based reading teaching design and SOLO-based reading teaching assessment. The review indicates that design research has consolidated a working model of tiered objectives, ascending tasks, and question chains, while assessment research has produced level descriptions, evaluation scales, and process-oriented frameworks. And the two lines converge on aligning objectives, activities, and assessment within one level system. The field nevertheless remains constrained by predominantly case-based methods, scarce controlled or longitudinal evidence, and uneven attention between junior and senior high schools. The review concludes that SOLO taxonomy provides an operational definition of thinking depth in reading and supports the integration of teaching, learning, and assessment, but that future work requires more rigorous empirical designs, validated instruments, and broader coverage of learners and reading contexts.

This study aims to analyze the integration between the cognitive process dimensions of Revised Bloom's Taxonomy and the structural complexity of the SOLO Taxonomy in questions constructed by pre-service biology teachers, as well as its correlation with students' cognitive learning outcomes. A descriptive-quantitative approach with co-relational analysis was employed, evaluating a total sample of 420 question sentences generated by students during their field teaching program (PPL). Data collection was conducted using double-coding observation rubrics and statistically processed via Spearman’s rho non-parametric correlation test. The results indicated a stark gradation phenomenon, with question distribution heavily accumulating within lower-order thinking skills (LOTS), predominantly spanning the Remembering (C1) and Understanding (C2) levels with Unistructural and Multistructural reasoning profiles. Conversely, higher-order thinking skills (HOTS) were strictly concentrated at the Analyzing (C4) and Evaluating (C5) levels, aligning with Relational and Extended Abstract structures. Statistical analysis revealed a positive and significant correlation coefficient (p = 0.707, p < 0.001), indicating a very strong linear relationship where higher cognitive demands inherently correspond to greater structural reasoning maturity. In conclusion, while pre-service teachers possess a solid foundation in factual knowledge, their capacity to formulate higher-order questions remains limited. Therefore, transforming classroom communication through constructivist learning strategies and gradual conceptual scaffolding is highly recommended to foster integrative thinking and bridge the cognitive transition toward deep conceptual understanding.