Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whether such information has truly become inaccessible remains challenging. Existing benchmarks primarily assess unlearning under clean, non-adversarial queries, leaving open whether information that appears forgotten can still be recovered through strategic prompting. We address this gap through a unified evaluation of prompt-based and fine-tuning-based unlearning methods on TOFU using Llama-3.2-3B-Instruct, followed by an adversarial robustness evaluation of methods that perform strongly under standard metrics. We introduce Attack Success Rate (ASR), an LLM-as-judge metric that measures the fraction of adversarial responses whose leakage score exceeds $0.2$, and evaluate recovery across eight attack suites. Our results reveal a substantial gap between clean-query forgetting and adversarial robustness. Although several fine-tuning-based methods achieve Forget Quality above $0.91$, targeted information remains recoverable with ASRs between $72.8\%$ and $84.3\%$, close to the $87.5\%$ ASR of the unprotected base model. In contrast, clean multilingual reformulations yield only $2.95\%$ measured leakage. A manual audit further finds agreement between binary ASR decisions and human factual assessments in seven of ten cases, indicating that ASR provides a useful, though imperfect, signal of behavioral recoverability. These findings show that strong standard-metric performance alone is insufficient to establish robustness after unlearning and motivate adversarial stress-testing as a complementary component of unlearning evaluation.
Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recovers held-out forget-set ROUGE for every method we evaluate, and we trace this fragility to optimization geometry. The per-token answer margin of fourteen post-hoc methods spanning gradient, preference, and distillation families converges into a narrow band above the retain reference in 41 of 42 method--size cells, a regularity we call the margin cliff. We prove that this cliff follows whenever the retain coupling holds the diagnostic log-odds of forget content above a floor, a condition that token-saturating losses induce at stationarity and that we verify directly on 34 of 42 cells. Margin Calibration (\textsc{MC}) is a plug-in polish adding a non-saturating margin hinge anchored at the reference's per-token margin plus a KL probe on a disjoint instruction corpus, restoring forget-side pressure where the native loss saturates. Under a stated gradient-dominance condition, whose on-trajectory gradient signature we measure by instrumenting the polish, its stationary set lies on the cliff-crossing side, yielding an attack-budget upper bound on the relearn margin lift. Across TOFU (three Llama-3 sizes, three forget tiers), MUSE-News on Llama-2-7B-hf, and a Phi-3.5 panel, a single frozen configuration wins all 14 head-to-head forget aggregates and all populated relearn cells (panel-mean post-attack ROUGE-L $0.41$ to $0.18$) and lowers raw membership AUC on 13/14, with reduced retain-side utility as the main cost. A deployment variant matches these gains without a retain-trained reference.
Chaoyi Xiang, Olga Ohrimenko, Benjamin I. P. Rubinstein +1cs.CL
Large language models (LLMs) can memorize sensitive facts, motivating unlearning methods that remove targeted knowledge without costly retraining. However, unlearning research remains heavily English-centric. We study multilingual unlearning by extending the TOFU benchmark to five languages, and fine-tune, unlearn, and query our models with different permutations of languages. We find that unlearning transfer, the ability of an unlearned model to "forget" facts in languages other than the unlearning language, is highly variable: e.g., it is strongest between languages sharing scripts and families, and we show that the unlearning language predicts which query languages are most likely to yield the strongest transfer. Layer-wise analysis reveals that unlearning leaves the shared cross-lingual latent space largely intact in early layers, instead operating primarily in later decoding layers. This suggests that unlearning does not truly erase knowledge, but rather induces superficial suppression. Exploiting this structure, a single inference-time steering direction reverses much of this suppression across languages, recovering 50% (Qwen) and 90% (Gemma) of the unlearned knowledge.