- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes LUCID, a framework for auditing whether a suspect language model was trained on outputs from a protected model. LUCID inserts suspect responses into a self-attribution prompt, extracts judge-token representations from the protected model, and trains an MLP classifier across multiple distillation settings. The framework requires only query access to the suspect model and internal access to the protected model. Experiments report strong detection performance across suspect (student) families and sizes, protected-model sizes, prompt styles, mixed-source training, audit question sets, and publicly released models.
Critical strengths
- Relevant problem and practical access assumptions. Retrospective auditing without modifying the protected model or embedding watermarks addresses a meaningful limitation of proactive protection methods. Requiring only text responses from the suspect model makes the framework applicable to restricted-access auditing scenarios.
- Strong results across several controlled settings. The evaluation includes held-out student families and prompt styles, larger students, mixed-source training, and independently trained test checkpoints. Matching student bases, training questions, and SFT configurations between infringing (positive) and non-infringing (negative) suspect models provides useful experimental controls.
Critical weaknesses
- The experiments do not sufficiently establish teacher-specific data provenance. In the main controlled experiments, positive models are trained on protected-model responses, whereas negative models are trained on ground-truth answers. This leaves open whether the detector identifies teacher-specific provenance or generic differences between training on model-generated long-CoT outputs and on reference solutions (e.g., reasoning style or response length). The failure of NFP-FS and NFP-BS (Sections 2.3 and 4.2) does not rule this out, since these are training-free similarity scores rather than supervised classifiers on surface features. In the mixed-source experiment (Section 4.4), the two classes still differ exactly in protected-model versus ground-truth s1k targets. Moreover, in the real-world evaluation (Section 4.5, Table 6), the infringing models are fine-tuned from the protected model itself (Appendix A.11, Table 13), whereas the non-infringing models come from unrelated model families (Table 14). Their detection therefore cannot isolate output-data distillation from weight lineage. These limitations weaken the interpretation of high classification accuracy as evidence of the claimed provenance signal.
- The distinctive contribution of judge-token representations is insufficiently isolated. The baselines (lexical similarity NFP-FS, BERTScore NFP-BS, and direct Self-Judge) are all training-free, whereas LUCID trains a supervised MLP on labeled checkpoints. The performance gap may therefore stem from supervision rather than from the self-attribution prompt or the protected model's representations. The ablations in Section 4.6 vary corpus size, feature layer, and audit question set, but not the prompt or the representation source. Controls such as the protected model's hidden states for the raw response without the self-attribution prompt, hidden states from an unrelated language model, or simple supervised surface-feature baselines (e.g., length and n-gram features) with the same classifier would clarify whether these components are necessary.
Questions for authors
- With the detector held fixed, what false-positive rate does LUCID achieve on students trained on another teacher's responses to the same questions, with comparable reasoning format and response length? How does LUCID behave on a suspect distilled from the protected model's own upstream teacher (DeepSeek-R1), and how is infringement defined in that case, given that Section 4.5 treats DeepSeek-R1 derivatives as infringing?
- How should Table 6 be interpreted given that its infringing models are fine-tuned from the protected model's weights? What evidence distinguishes detection of output-data provenance from detection of weight lineage?
- In one representative setting, how does LUCID compare with the same classifier using (a) the protected model's representations of the raw response without the self-attribution prompt, (b) representations extracted by another language model, and (c) supervised surface features such as response length and n-grams?
I'll consider raising score if my questions are addressed.