Metraipolis › archive › dc_7aa457863830
Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing — arXiv:2609.28026
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28026
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T09:13:14.935Z
- SHA-256 of the archived text
012593d33c1742a2382b3be6c5ecc10fb86de45387c6c0a1c3754622982521ec- Stable URL of this page
https://metraipolis.com/documento/dc_7aa457863830
How to cite
Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing — arXiv:2609.28026 — arXiv (en), https://arxiv.org/abs/2609.28026 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7aa457863830 (Metraipolis archive dc_7aa457863830, sha256 012593d33c1742a2382b3be6c5ecc10fb86de45387c6c0a1c3754622982521ec)
BibTeX
@misc{dc7aa457863830,
title = {Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing — arXiv:2609.28026},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28026},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7aa457863830; sha256 012593d33c1742a2382b3be6c5ecc10fb86de45387c6c0a1c3754622982521ec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28026. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We investigate whether state-of-the-art large language models (LLMs) generate feedback that reflects the pedagogical practices of expert teachers in terms of feedback focus and adaptivity. Previous evaluation efforts have examined feedback characteristics, its impact on learning, and its target, yet the focus of feedback and its adaptivity remains largely overlooked. To bridge this gap, we adopt and refine Narciss's taxonomy into seven feedback focus types to annotate teacher and LLM-generated feedback across three university writing courses. We release FeedType, a benchmark containing annotated teacher and LLM feedback from six LLMs under three prompting strategies. We assess the coverage and distribution of feedback focus types, and examine whether LLMs adapt their feedback across draft stages and student performance levels as an expert instructor does. Our findings show that while most LLMs cover most feedback focus types, they fail to reflect teacher feedback distributions and show varying levels of adaptivity, with none matching the teachers' adaptive behavior. We believe FeedType will support future research on pedagogical alignment in LLM feedback generation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.28026 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T08:13:26.741Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).