Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters

Abstract

Adapters are often selected and deployed based on nominal labels (e.g., instruction-tuned), which implicitly suggest what capability improves after adaptation. We test whether nominal training objectives reliably align with realized cross-task capability gains by evaluating the same LoRA adapter across tasks. Our strongest evidence is tied to strict, automatically verifiable instruction following as measured by IFEval: across multiple seeds, base models, and LoRA settings, nominal labels recurrently but not universally fail to predict improvements on this verifiable target, with clear configuration sensitivity including a near-zero or negative case. As an illustrative strongest-case example in a controlled instruction-versus-numeric setting, an instruction-tuned adapter substantially improves off-target NM-based numeric benchmark performance from 0.133 to 0.632 while not improving verifiable instruction following on IFEval (ILA: 0.313 to 0.271; PLA: 0.250 to 0.143; values rounded to three decimals). We refer to this nominal-versus-realized mismatch pattern as capability drift as a descriptive label. The mismatch is visible in the raw cross-task performance matrix; we use a drift score only as a compact summary in the same units as the underlying metrics, not as a new formal metric contribution. Evidence from broader instruction-following benchmarks is benchmark-dependent and mixed, reflecting heterogeneity in how instruction following is operationalized; we therefore do not treat cross-benchmark agreement as a premise. Overall, the practical takeaway is to perform routine cross-task evaluation before deployment and to avoid treating nominal labels as reliable capability proxies.

Figures (5)

• Figure 1: Drift score summary. Heatmap of $\mathrm{DriftScore}(a\rightarrow b)$ computed from cross-task evaluation metrics. Compact overview of score magnitudes from the same evaluations; see §\ref{['sec:robustness']} for context.
• Figure 2: Robustness quadrant plot (primary evidence). Per-run target gain on IFEval PLA (instr$-$base) versus off-target gain on numeric NM (instr$-$base) for the robustness evaluations underlying \ref{['tab:robustness']} and Appendix \ref{['tab:robustness_drift']}. Most points lie above $y{=}x$ (positive drift), with occasional near-zero or negative cases.
• Figure 3: Selective shifts in verifiable instruction following (IFEval). Category-level and type-level shifts for the instruction adapter relative to base on IFEval. This breakdown is qualitative; low-support types should be interpreted cautiously.
• Figure 4: Upper-layer geometry diagnostics. Top modules by geometric similarity between instruction- and numeric-reasoning-tuned LoRA updates. This figure provides preliminary evidence but does not establish a localized causal mechanism.
• Figure 5: Functional probing summary with null or small effects. Largest observed effect sizes from localized functional probing. We do not find strong localized causal evidence that explains the mismatch pattern in this setup.