Metraipolis › archive › dc_2b0f9205ebfc
Grammar Concept Annotation at Scale: Deployed Fine-Tuned Small Language Models Outperform Prompted Frontier Models — arXiv:2610.10827
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10827
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:55:57.429Z
- SHA-256 of the archived text
58e9c57031bc4fc21cd42bfc177ea65d55adbf99280779458bc928ea816b39f8- Stable URL of this page
https://metraipolis.com/documento/dc_2b0f9205ebfc
How to cite
Grammar Concept Annotation at Scale: Deployed Fine-Tuned Small Language Models Outperform Prompted Frontier Models — arXiv:2610.10827 — arXiv (en), https://arxiv.org/abs/2610.10827 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b0f9205ebfc (Metraipolis archive dc_2b0f9205ebfc, sha256 58e9c57031bc4fc21cd42bfc177ea65d55adbf99280779458bc928ea816b39f8)
BibTeX
@misc{dc2b0f9205ebfc,
title = {Grammar Concept Annotation at Scale: Deployed Fine-Tuned Small Language Models Outperform Prompted Frontier Models — arXiv:2610.10827},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10827},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b0f9205ebfc; sha256 58e9c57031bc4fc21cd42bfc177ea65d55adbf99280779458bc928ea816b39f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10827. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Corrective feedback is among the best-evidenced drivers of second-language acquisition, yet corrections delivered during lessons rarely accumulate into an actionable view of grammar mastery. Prompted frontier models can provide such a view from learner--tutor lesson transcripts, but they are costly at scale. We close this gap by fine-tuning Qwen3.5 small language models (SLMs) on filtered and rebalanced teacher-generated supervision, then deploying an efficient 0.8B model in an end-to-end grammar mastery tracker for all English learners on our platform. Internalizing the annotation contract into adapter weights enables pairing the 0.8B model with a compact matched prompt rather than verbose instructions. On two human-curated benchmarks, both the deployed 0.8B model and a 4B reference comparator outperform prompted GPT-5.4 and GPT-5.6 Sol in precision and recall under nested matching criteria of increasing strictness: concept, evidence span, and correctness. The deployed 0.8B SLM reduces serving cost by approximately 16$\times$. A feature-level online experiment shows significant gains in learner engagement ($+15.8\%$) and key business metrics, including scheduled hours ($+2.1\%$) and GMV from new lessons ($+13.2\%$). Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.10827 — 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 2026-10-09T05:47:01.388Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).