- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents DETER, which combines pretraining data filtering with periodic gradient-ascent unlearning during pretraining stage on selected target corpus to increase the cost of subsequent relearning, achieving a tamper resistance. The paper implements series of experiments which target medical knowledge in language models ranging from 113M to 521M parameters and compares against document filtering, token-level filtering, and post-hoc unlearning. Recovery is measured by the PubMed finetuning tokens needed to reach the unfiltered baselines' PubMed loss. At 512M setting, after unlearned by DETER, it requires approximately 13.5 times more tokens than document filtering alone, with a relatively small increase in general-domain loss.
Critical strengths
-
The paper uses a periodic gradient ascent on target-domain data in ordinary pretraining, achieving effective suppression of medical knowledge and increasing the difficulty of recovering it through subsequent finetuning. DETER adds only a few training compute while substantially increasing the finetuning data required for recovery—by up to 13.5× over filtering alone under the paper’s PubMed loss criterion. Besides, DETER can potentially become a interpretable method for other domain in LLM.
-
The paper implement a large number of experiments including comparison with baselines and ablation studies.
Critical weaknesses
- Justification of the recovery criterion: In this paper, the unfiltered baseline's PubMed corpus loss is used as the criterion to judge if the unlearned model has been successfully recovered, however, in llm the improvements in perplexity do not necessarily translate into better downstream task performance.
- Understanding the source of increased recovery difficulty: DETER requires more finetuning tokens to reach the reference PubMed loss, but it remains unclear whether this primarily reflects its higher loss after unlearning or whether the parameter configurations induced by suppression make subsequent optimization more difficult.
- There are more baseline methods needed to be evaluated. And more seeds for pretraining need to be evaluated
- Ambiguity in the scope of the claims: Since all target domain suppression and recovery experiments focus on medical knowledge, the main claims should be explicitly scoped to this setting. Although the limitations section acknowledges this boundary, reflecting it consistently in the abstract and contribution statements would make the contribution clearer.
Questions for authors
- Could authors clarify why corpus loss is an appropriate criterion for capability recovery, and whether it offers advantages over accuracy or task success evaluations in this medical domain setting? The evidence that can establish the correspondence between this criterion and actual task performance would strength the evaluation. Otherwise, supplementing current results with direct performance metrics would provide more convincing evidence of whether recovery has occurred.
- DETER requires more finetuning tokens to reach the reference PubMed loss. It would be helpful if the authors briefly discussed how this result may reflect both the higher loss after unlearning and possible changes in subsequent optimization dynamics arising from the learned parameter configurations. This is a request for clarification rather than additional experiments, and does not dispute the method’s observed unlearning effects. A clearer account of the underlying mechanism would strengthen the contribution.
- Given the relevance of SGTM and TAR to pretraining time capability removal and tamper resistance, could the authors clarify why these methods were left for future comparison rather than included in the current evaluation?
- The experiments use a single pretraining seed per configuration, while the reported repetitions vary the fine-tuning seeds. Could the authors discuss how pretraining variability might affect the reported gains, particularly the scaling trend?
- It will make the paper clearer if authors can make the claim clearer.
If authors can provide reasonable explanations for 1. 2. 3. 4. I can keep the decision as weak acceptance, otherwise I will consider dropping the score to the weak rejection
Hi Reviewers,
The authors have provided responses. Please check if they have addressed your concerns.
Thanks, AC