الملخص
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.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Chang, Y., & Wu, Y. (2026). CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation. https://omanscience.com/ar/articles/calibudget-calibration-guided-source-allocation-for-fixed-budget-mixed-reasoning-adaptation
MLA 9
Chang, Yupeng, and Yuan Wu. "CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation." https://omanscience.com/ar/articles/calibudget-calibration-guided-source-allocation-for-fixed-budget-mixed-reasoning-adaptation.
شيكاغو (المؤلف–التاريخ)
Chang, Yupeng, and Yuan Wu. 2026. "CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation." https://omanscience.com/ar/articles/calibudget-calibration-guided-source-allocation-for-fixed-budget-mixed-reasoning-adaptation.
هارفارد
Chang, Y. and Wu, Y. (2026) 'CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation', Available at: https://omanscience.com/ar/articles/calibudget-calibration-guided-source-allocation-for-fixed-budget-mixed-reasoning-adaptation.
فانكوفر
Chang Y, Wu Y. CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation. https://omanscience.com/ar/articles/calibudget-calibration-guided-source-allocation-for-fixed-budget-mixed-reasoning-adaptation
IEEE
Y. Chang, and Y. Wu, "CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation," https://omanscience.com/ar/articles/calibudget-calibration-guided-source-allocation-for-fixed-budget-mixed-reasoning-adaptation.