cs.CLNov 5, 2026

Guardrail Erosion in Domain Fine-Tuned Large Language Models: A Paired Audit of Knowledge-Centric Abstention in Biomedical LLMs

Authors: Stephen Peng, Vineet Jagadeesan Nair, Noah Broestl, Anne Friederike Kleppe, Steven Mills, Adi Zolotov

Organizations: BCG X AI Science Institute, Boston Consulting Group · Centre for Human-Inspired Artificial Intelligence, University of Cambridge

Abstract

The number of domain fine-tuned models, particularly in the biomedical domain, is rapidly expanding. Fine-tuning promises high-performing models at a fraction of the cost of training a base model, but it can also produce unintended behavioral changes. Multiple studies have shown that safety guardrails can erode with fine-tuning, yet large-scale studies across model architectures, data mixtures, and fine-tuning methodologies remain limited. Where prior work in this space has studied value-centric refusal, this work focuses on knowledge-centric abstention. We audit 25 biomedical domain fine-tuned large language models against 11 paired base checkpoints on MedAbstain and ClinDet-Bench to evaluate the impact of fine-tuning on knowledge-centric abstention. We find that defined appropriate abstention measured by these benchmarks, already low in base models (median 8.3% on MedAbstain), falls further after fine-tuning (median 4.2%, decreasing in 21 of 25 pairs on MedAbstain), and that the magnitude and direction of change are heterogeneous across pairs. These results motivate fine-tuning methods that improve domain-specific capability while preserving appropriate caution.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Nov 6, 2026

Restoring General and Improving Domain-Specific Safety in Fine-Tuned LLMs Without Retraining

Safety-aligned language models are known to suffer degradation in refusal behavior following domain-specific fine-tuning, even when the fine-tuning data is entirely benign. The predominant mitigation strategy, preference optimization on the fine-tuned model, is computationally expensive and requires domain-specific preference data that is often unavailable in practice. We propose SPECTRA, a training-free, weight-level method that restores refusal behavior by transferring the base model's refusal direction into the fine-tuned model's weights via an activation-aware, low-rank update, requiring no gradient-based optimization or domain-specific safety data. The low-rank design restricts the intervention to the subspace most causally active on harmful inputs, leaving benign behavior largely undisturbed by construction. Empirically, SPECTRA substantially improves refusal behavior across a comprehensive safety evaluation, while preserving general coherence, domain-specific knowledge, and producing negligible change in false refusal rates.
Jun 2, 2026

Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability

Adapting foundation large language models to a user's task or preferred style through fine-tuning can result in compromising the model's safety. Previous works examined the effects of fine-tuning on model safety in limited and seemingly random experimental settings. We argue that anchoring fine-tuning to a specific capability goal is essential for avoiding arbitrary empirical choices, allowing us to draw meaningful conclusions about safety impacts, and to compare mitigation methods on a consistent basis. We conduct a multi-dimensional evaluation of the effects of fine-tuning on model behavior by focusing on capability as well as safety. Our results surface important issues that (1) fine-tuned models can produce incoherent generations in response to safety prompts, (2) automated safety judgments are unreliable for such incoherent outputs, and (3) the conclusions about the effects of fine-tuning can change depending on the choice of safety benchmark as well as the safety evaluator.
Oct 19, 2026

Safety Offset Learning: When Benign Fine-Tuning Misaligns LLMs

Safety risks from fine-tuning are commonly characterized by the harmfulness of the training data:harmful fine-tuning is considered dangerous, while benign fine-tuning is often assumed to preservealignment. We argue that this view misses a more fundamental factor-the behavioral transition inducedby supervision. Harmful fine-tuning and safety-degrading benign fine-tuning can both be understoodas learning the same refusal-to-compliance transition, but on different data distributions. We studywhether such a transition learned on benign inputs can generalize to harmful requests. We constructbenign examples that an aligned model initially tends to refuse and pair them with their originalharmless responses, creating a discrepancy between the model's initial refusal and the supervisedanswer. Fine-tuning on these examples increases harmful compliance, but only when two conditionshold together: the discrepancy is large enough, and it cannot be resolved through a narrow surface-levelshortcut. With the induced discrepancy matched, varying only whether it is localized changes harmfulcompliance by an order of magnitude; raising the discrepancy does not help while a shortcut remainsavailable, and removing the shortcut does not help while the discrepancy is small. Building on thisobservation, we introduce SAFEOFF, a dataset of benign instructions rewritten to raise the alignedmodel's refusal likelihood and paired with their original answers. Across three aligned LLMs and threesafety benchmarks, SAFEOFF substantially weakens safety alignment despite containing no explicitharmful supervision, suggesting that fine-tuning safety depends not only on what data a model sees, butalso on which behavioral boundary the supervision moves.