Metraipolis › archive › dc_99d2f253b729
CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation — arXiv:2609.36721
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36721
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:29:24.427Z
- SHA-256 of the archived text
8520bd2eb3e74eab765495302ed03ed195f96aa50be88e4d0cf05ff9fb30805c- Stable URL of this page
https://metraipolis.com/documento/dc_99d2f253b729
How to cite
CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation — arXiv:2609.36721 — arXiv (en), https://arxiv.org/abs/2609.36721 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99d2f253b729 (Metraipolis archive dc_99d2f253b729, sha256 8520bd2eb3e74eab765495302ed03ed195f96aa50be88e4d0cf05ff9fb30805c)
BibTeX
@misc{dc99d2f253b729,
title = {CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation — arXiv:2609.36721},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36721},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99d2f253b729; sha256 8520bd2eb3e74eab765495302ed03ed195f96aa50be88e4d0cf05ff9fb30805c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36721. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fixed-budget adaptation from heterogeneous data sources requires deciding not only how much data to use, but how much exposure each source receives. Size-proportional rules can crowd out small sources, whereas difficulty-only rules can chase noisy estimates or allocate residual budget to nearly saturated pools. We introduce CALIBUDGET, a floor-protected, reliability-aware integer allocator that treats source exposure as an explicit adaptation variable. From small train-internal calibration splits, it combines model need, post-floor availability, and bootstrap stability, then produces exact capacity-respecting quotas without changing the model, objective, or total budget. In a controlled setting combining mathematical and commonsense data, CALIBUDGET improves CommonAvg, FragileAvg, and MacroAvg over validation-error-with-floor, the strongest matched comparator, in all three paired LLaMA-2-7B LoRA+ runs. The respective mean gains are 0.56, 0.46, and 0.41 percentage points (pp). Overall increases by 0.18 pp, whereas MathAvg decreases by 0.20 pp, exposing a coverage-retention boundary rather than a uniform gain. CALIBUDGET changes only 1.14-1.42% of the source budget but improves performance in 15 of 24 comparisons across commonsense tasks and seeds. These results suggest that small changes in source quotas can matter; example-level selection can then determine which examples fill each quota. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.36721 — 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 2026-10-07T16:59:48.225Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).