Metraipolis › archive › dc_ade16c8c8f12
Universal Textual Teaching for LLMs — arXiv:2610.12114
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.12114
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:48:31.826Z
- SHA-256 of the archived text
8a9d456442edb89402d1cc3d9afd9e9f55fbd55764be81b1db41be83fcd5640f- Stable URL of this page
https://metraipolis.com/documento/dc_ade16c8c8f12
How to cite
Universal Textual Teaching for LLMs — arXiv:2610.12114 — arXiv (en), https://arxiv.org/abs/2610.12114 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ade16c8c8f12 (Metraipolis archive dc_ade16c8c8f12, sha256 8a9d456442edb89402d1cc3d9afd9e9f55fbd55764be81b1db41be83fcd5640f)
BibTeX
@misc{dcade16c8c8f12,
title = {Universal Textual Teaching for LLMs — arXiv:2610.12114},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.12114},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ade16c8c8f12; sha256 8a9d456442edb89402d1cc3d9afd9e9f55fbd55764be81b1db41be83fcd5640f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12114. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby binding the distilled knowledge to a specific architecture and checkpoint. This implicit representation is difficult to interpret or reuse across models and limits KD for API-only or costly-to-train models. This paper studies knowledge transfer for large language models (LLMs). We introduce Universal Textual Teaching (UTT), a parameter-update-free framework that distills observed Teacher-Student knowledge gaps into a textual, interpretable, and reusable natural-language artifact called Primer. Specifically, UTT first identifies representative gap cases through paired evaluations, and iteratively updates the Primer via multi-role interactions: the Student attempts each task, the Prompter turns evaluation feedback into a teaching instruction, the Teacher provides a targeted demonstration, and the Synthesizer consolidates validated lessons. Empirically, on the challenging math (Omni-MATH-2) and code generation (KernelBench) tasks, extensive results confirm the effectiveness of the method: UTT remarkably raises the Student's accuracy from 9.4% to 48.6% and Fast1 accuracy from 9% to 35% on KernelBench, while increasing mathematical reasoning accuracy from 27.6% to 51.7%. UTT also performs better than representative prompt engineering and parameter-based KD methods. Of note, UTT is shown to be generalizable across different Teachers and Students: a Primer synthesized for one Teacher-Student pair can generalize to other Students that do not participate in the synthesis. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.12114 — 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 2026-10-09T05:47:01.011Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).