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

TL;DR

This paper investigates whether nominal instruction-tuning labels reliably predict actual cross-task capability improvements, revealing significant mismatches and emphasizing the importance of cross-task evaluation before deployment.

Contribution

It introduces the concept of capability drift, demonstrating that nominal labels often do not align with real performance gains across tasks, supported by extensive empirical evaluation.

Findings

Nominal labels often fail to predict actual capability improvements.

Instruction-tuned adapters can improve on off-target benchmarks without enhancing verifiable instruction following.

Cross-task evaluation is essential before deploying models to ensure capability alignment.

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.