Metraipolis › archive › dc_356fe47bb20e

LoRA Fine-Tuned Models for Control Systems Course Q\&A: A Multidimensional Evaluation of Model Scale and Rank Effects — arXiv:2609.13918

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13918
License (as archived): CC0-1.0
Archived: 2026-10-15T22:47:26.012Z
SHA-256 of the archived text: 69be9d0d03ce53043f74686cd5b687af15461b535e30896ed980f2c175e41ada
Stable URL of this page: https://metraipolis.com/documento/dc_356fe47bb20e

How to cite

LoRA Fine-Tuned Models for Control Systems Course Q\&A: A Multidimensional Evaluation of Model Scale and Rank Effects — arXiv:2609.13918 — arXiv (en), https://arxiv.org/abs/2609.13918 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_356fe47bb20e (Metraipolis archive dc_356fe47bb20e, sha256 69be9d0d03ce53043f74686cd5b687af15461b535e30896ed980f2c175e41ada)

BibTeX

@misc{dc356fe47bb20e,
  title = {LoRA Fine-Tuned Models for Control Systems Course Q&A: A Multidimensional Evaluation of Model Scale and Rank Effects — arXiv:2609.13918},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13918},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_356fe47bb20e; sha256 69be9d0d03ce53043f74686cd5b687af15461b535e30896ed980f2c175e41ada},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13918. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used in specialized university courses, but control-systems questions require coordinated terminology, notation, derivations, and stepwise explanations. Direct general-purpose responses may be inconsistently structured and hard to verify. Using exercises and reference solutions from a Linear Control Systems course, we built a supervised fine-tuning dataset of 360 system-user-assistant conversations. We applied LoRA to Qwen2.5-3B-Instruct and Qwen2.5-7B-Instruct. With identical data splits, inference settings, and evaluation protocols, we compared base and fine-tuned models and tested LoRA ranks r=4, 8, and 16. Evaluation used ROUGE, BERTScore, and structured-output features to measure reference-answer similarity and stability of the Solution-Method-Teaching Points format. LoRA improved both similarity and structured-output stability at both sizes. On the current test set, 7B-r16 achieved the highest ROUGE-L (0.4093) and BERTScore-F1 (0.8643), while r=8 offered a better balance between performance and parameter efficiency. Bootstrap resampling showed ROUGE-L gains of 0.0764 [0.0613, 0.0915] for 3B-r16 and 0.0874 [0.0687, 0.1042] for 7B-r16; both intervals exceeded zero, indicating stable textual-similarity improvements on the current test set. These results suggest LoRA can align open-source instruction-tuned models more closely with the language and pedagogical organization of course reference answers. However, the metrics mainly capture textual similarity and formatting consistency, not domain-specific reasoning or mathematical correctness, which require expert assessment and task-specific rubrics.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.13918 — 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 2026-10-15T22:29:03.159Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).