- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes TOLD, a query-only unlearning method that distills an in-context unlearning prompt into model parameters. A frozen teacher evaluates student-generated responses with and without the prompt. TOLD selectively transfers probability changes for vocabulary tokens through a KL objective. Experiments cover single-target unlearning on RWKU and additional evaluation on MUSE-Books.
Critical strengths
- Avoiding reference answers and a separate external teacher is practically useful. The method uses the base model to provide supervision and removes the need for an unlearning prompt at inference time. This reduces response-curation requirements and offers a straightforward way to turn prompt-based behavior into a parameter update.
- The evaluation considers neighboring knowledge as well as forgetting, which is important for entity-level unlearning. TOLD preserves neighboring knowledge well on Llama, and the Full-KLD comparison provides some evidence that selective distillation can reduce collateral damage. The additional MUSE-Books results also provide an initial test beyond individual entities.
Critical weaknesses
- The model coverage is too narrow. The experiments use only Llama-3.2-3B and Phi-3-mini, both from 2024 and both in the 3–4B range. There is no meaningful scaling study and no evaluation on recent Qwen or Gemma models. Since TOLD relies on the model’s own prompt-following ability to generate supervision, its effectiveness may depend strongly on the backbone.
- The main results do not establish a clear advantage. Averaging the three forgetting columns in Table 1, TOLD’s Llama forget recall is about 0.294, compared with about 0.280 for both NPO and Full-KLD, where lower is better. TOLD improves neighboring retention, but this is a trade-off rather than stronger forgetting. On Phi, it improves QA and adversarial forgetting, but has the lowest reported fluency score, 5.848 versus 6.737 for the base model. These mixed results require comparisons at matched forgetting or retention levels, not just isolated operating points.
- The baseline comparison is not sufficiently controlled. Table 2 uses different learning rates, effective batch sizes, and training lengths, but provides no comparable search budgets or common selection rule. TOLD receives backbone-specific selection, while baselines use settings from their released implementations. The total search budget for TOLD is also unclear. A documented tuning protocol, such as the one used in OpenUnlearning, is needed. Moreover, TOLD trains on 300 non-target queries, whereas the listed GA and NPO objectives contain no retain term. Comparisons with GradDiff or NPO plus retention, using the same non-target data, would better test the claimed retention advantage.
- The central design choices are not cleanly validated. There is no controlled on-policy versus off-policy comparison. DUET also differs in which response positions are distilled, so beating DUET does not isolate the benefit of on-policy sampling. The Full-KLD comparison has another potential confound: TOLD uses on Phi, while Full-KLD is described as directly matching the ICU distribution. It is unclear whether intervention strength and clipping are matched. Similarly, bidirectional selection can modify up to vocabulary entries, but the paper does not establish that the one-sided ablations use the same total token budget. Without these controls, the gains cannot be confidently attributed to the proposed components.
- The privacy and robustness evidence is weak. The forget-member loss barely changes: from 2.429 to 2.432 on Llama and from 1.932 to 1.933 on Phi. These results provide little evidence of reduced memorization under the paper’s own measure. The “MIA” columns report average passage losses, not attack performance such as ROC-AUC or attack success at a fixed false-positive rate. Robustness is assessed using the provided RWKU prompt suite and ROUGE-L, without adaptive extraction tests or a semantic check of whether target facts remain recoverable. The paper acknowledges behavioral suppression, but even within that scope, stronger evidence is needed.
- Reproducibility and computational cost are insufficiently documented. The anonymous repository lacks a README, leaving no clear starting point for reproducing the experiments.
Questions for authors
- What search spaces, trial counts, and selection criteria were used for every method, including TOLD? Does TOLD retain its advantage after comparable tuning and after giving retention-aware baselines access to the same non-target data?
- Can the authors provide controlled on-policy versus off-policy results? For Full-KLD and the one-sided ablations, were , clipping, and the total number of selected vocabulary entries matched?
- Why do the forget-member losses remain almost unchanged? Can the authors report actual membership-inference performance and test whether adaptive prompts recover target facts that the current evaluation misses?
- Can the authors show that the findings hold beyond the 3–4B range and on more recent families, such as Qwen3.5 or Gemma 4? In particular, does the forgetting–retention advantage remain after tuning the baselines on these models?
- Can the authors provide a README, exact reproduction commands, search configurations, and per-target runtime and memory measurements, including student generation and teacher evaluation?