{"slug": "a-feasibility-study-on-retrieval-practice-using-large-language-models", "title": "A Feasibility Study on Retrieval Practice Using Large Language Models", "summary": "A feasibility study by Marcus Leong, Jennifer Rose, Lisa Dierker, and Antonio Laverghetta Jr., published in the Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con) on pages 194–203, found that LLM-generated retrieval practice items for an introductory psychology course exhibited overall weaker psychometric properties than instructor-written items. The authors conclude that human supervision may remain necessary during item generation for retrieval practice.", "body_md": "##### Abstract\n\nRetrieval practice supports learning but requires educators to build large item banks. We compared LLM-generated and human-written retrieval practice items in an introductory psychology course to test whether LLM items match instructor-written ones in quality. LLM items exhibited overall weaker psychometric properties, suggesting that human supervision may remain necessary during item generation for retrieval practice.\n- Anthology ID:\n- 2026.aimecon-main.21\n- Volume:\n- [Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers](https://aclanthology.org/volumes/2026.aimecon-main/)\n- Month:\n- October\n- Year:\n- 2026\n- Address:\n- Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States\n- Editors:\n- [Joshua Wilson](https://aclanthology.org/people/joshua-wilson/unverified/) ,[Christopher Ormerod](https://aclanthology.org/people/christopher-ormerod/unverified/) ,[Magdalen Beiting-Parrish](https://aclanthology.org/people/magdalen-beiting-parrish/unverified/)\n- Venue:\n- [AIME-Con](https://aclanthology.org/venues/aimecon/)\n- SIG:\n- Publisher:\n- National Council on Measurement in Education (NCME)\n- Note:\n- Pages:\n- 194–203\n- Language:\n- URL:\n- [https://aclanthology.org/2026.aimecon-main.21/](https://aclanthology.org/2026.aimecon-main.21/)\n- DOI:\n- Cite (ACL):\n- Marcus Leong, Jennifer Rose, Lisa Dierker, and Antonio Laverghetta Jr.. 2026. [A Feasibility Study on Retrieval Practice Using Large Language Models](https://aclanthology.org/2026.aimecon-main.21/) . In*Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers* , pages 194–203, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).\n- Cite (Informal):\n- [A Feasibility Study on Retrieval Practice Using Large Language Models](https://aclanthology.org/2026.aimecon-main.21/) (Leong et al., AIME-Con 2026)\n- PDF:\n- [https://aclanthology.org/2026.aimecon-main.21.pdf](https://aclanthology.org/2026.aimecon-main.21.pdf)", "url": "https://wpnews.pro/news/a-feasibility-study-on-retrieval-practice-using-large-language-models", "canonical_source": "https://aclanthology.org/2026.aimecon-main.21/", "published_at": "2026-10-02 00:00:00+00:00", "updated_at": "2026-10-03 22:08:58.131873+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "generative-ai"], "entities": ["Marcus Leong", "Jennifer Rose", "Lisa Dierker", "Antonio Laverghetta Jr.", "AIME-Con", "National Council on Measurement in Education"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/a-feasibility-study-on-retrieval-practice-using-large-language-models", "markdown": "https://wpnews.pro/news/a-feasibility-study-on-retrieval-practice-using-large-language-models.md", "text": "https://wpnews.pro/news/a-feasibility-study-on-retrieval-practice-using-large-language-models.txt", "jsonld": "https://wpnews.pro/news/a-feasibility-study-on-retrieval-practice-using-large-language-models.jsonld"}}