AI evidence extraction

Through the looking glass: a synthesis of systematic reviews and meta-analyses on pedagogy paradigms facilitated by large language models

Boulus Shehata, Asha Kanwar, Dejian Liu, Zehao Liu · Smart Learning Environments · 2026

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

5/10

Relevance

1/4

Quality (LMQS)

Evidence

Citations

0.00

FWCI

This is an AI analysis. Read the peer-reviewed original at the publisher: https://doi.org/10.1186/s40561-026-00449-x

Methodology & findings

Study design

Systematic synthesis of reviews and meta-analyses adhering to PRISMA guidelines and AMSTAR checklist.

Sample

N = 50, 2 groups

Primary method

Systematic synthesis following PRISMA guidelines and AMSTAR checklist for quality assessment of included reviews. Narrative synthesis of trends in publication year, geographic regions, types of reviews, research questions, pedagogy paradigms, and challenges.

Main result

The synthesis revealed that "constructivism, cognitivism, and connectivism emerged as the most frequently addressed paradigms, indicating the role of LLMs as (i) tools for learning discovery or scaffolding, where learners actively construct knowledge, (ii) tools to improve cognitive tasks (e.g., recall, comprehension, problem-solving), or (iii) tools to facilitate connections between diverse knowledge sources or enable networked learning environments."

Reports effect sizes.

Research paradigm

Pragmatist/Systematic review synthesis

Author conclusions

The authors conclude that "this study offers valuable insights into the evolving roles of LLMs in facilitating paradigms that contribute to a deeper understanding of the pedagogical implications, challenges, and opportunities presented by LLM adoption in education."

Risk of bias

Publication bias in included reviews; Heterogeneity in methodology and quality of included reviews; Geographic and temporal publication bias; Selection bias in the original reviews synthesized; Publication bias (only published reviews included); Selection bias in choice of 50 reviews; Potential heterogeneity in review quality across included reviews; Geographic bias (depending on database coverage); Potential publication bias in included reviews; Geographic variation in review coverage not fully characterized; Heterogeneity in review methodologies and quality across the 50 included reviews; Selection bias in which reviews were included based on search strategy

Open questions raised

The synthesis identifies several challenges and gaps: cognitive load and processing, accuracy and comprehension, cultural sensitivity and diversity, and learner autonomy and self-expression. Future directions include addressing these challenges and further exploring how LLMs can be optimized for different pedagogical paradigms.
The synthesis identifies gaps related to: (1) underexplored pedagogy paradigms beyond constructivism, cognitivism, and connectivism; (2) limited research on specific challenges including cognitive load, accuracy, cultural sensitivity, and learner autonomy; (3) need for future directions in LLM adoption in education.
The study identifies gaps including: cognitive load and processing challenges, accuracy and comprehension issues, cultural sensitivity and diversity concerns, and learner autonomy and self-expression limitations. Future research directions focus on understanding how LLMs can better address these challenges while facilitating different pedagogical paradigms.

Data: not_statedCode: not_statedExtracted from: pdfAgreement 65%

Explore related topics

Human-AI Collaboration Meta-Analysis