← All publications

Replicating Validation-Selected Weight Interpolation on SmolLM2-360M Base and Instruct: ARC, HellaSwag and WinoGrande

Dheiver Francisco Santos, PhD · Preprint, Figshare, 15 November 2026 · CC BY 4.0 · doi:10.6084/m9.figshare.35014000 · ORCID 0000-0002-8599-9436

Abstract

Selecting an interpolation coefficient between a base language model and its instruct sibling is often presented as a free improvement over both. We replicate a pre-registered test of this claim on SmolLM2-360M and its instruct version, using the same protocol as for Qwen2.5-0.5B with a coarser six-point grid, selection on 300 validation items per task, and 3,967 disjoint test items. The selected t^*=0.2 scores 55.86% on test against 55.40% for the base model: +0.46 pp (95% paired bootstrap CI [-0.10,+1.02], p=0.113). The interval contains zero, so the hypothesis is not supported. Unlike the Qwen pair, the instruct model is worse than the base model on these log-likelihood benchmarks (no chat template), by -5.64 pp (95% CI [-6.89,-4.35]). Merge accuracy declines from t=0.4 to 1.0; t=0.6 is not distinguishable from the base. A small-t merge is statistically indistinguishable from the base model (no equivalence test). Two model pairs and one hardware platform limit what can be concluded.

Download the PDF · Figshare record and reproducibility package

Cite as: D. F. Santos, “Replicating Validation-Selected Weight Interpolation on SmolLM2-360M Base and Instruct: ARC, HellaSwag and WinoGrande,” Figshare, 2026, doi:10.6084/m9.figshare.35014000.