- Rating
- 2
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces ancestral membership auditing, which asks whether a source document contributed to downstream fine-tuning indirectly through synthetic examples generated from that source, even when the source itself and the actual synthetic training examples are unavailable to the auditor. The authors identify the Sibling Transfer Effect (STE): independently regenerated examples from a member source tend to exhibit more favorable changes in answer likelihood than examples generated from nonmember sources.
The proposed audit generates source-grounded QA "siblings" and scores them using the target model, optionally calibrated against the pretrained base or separately fine-tuned reference models. The strongest variant, Multi5, uses five reference models.
Experiments cover Enron and BillSum, eight target-model families, and three synthetic-data generators. Multi5 obtains mean AUCs of 0.9240/0.9477 with matched generators and 0.8328/0.8504 under generator mismatch. Importantly, removing exact matches to the hidden training examples barely changes performance, while shuffling source-sibling relationships reduces AUC to approximately 0.5. The signal is also substantially stronger when regenerated siblings share evidence with the hidden descendants.
Critical strengths
-
Strong controls supporting the claimed mechanism. The most convincing aspect is that the authors go beyond showing a membership-classification signal. Removing audit QA that exactly matches the target training records produces almost no degradation, while randomly shuffling sibling families across sources reduces performance to chance. This provides good evidence that the reported effect is not simply memorization or accidental regeneration of training records.
-
Broad evaluation across models and generator mismatch. The effect is demonstrated across eight model families, two domains, and both matched and mismatched provider/auditor generators. The cross-generator AUCs remain substantially above chance, which makes the result considerably more interesting than an effect that depends on reproducing the original generation pipeline.
Critical weaknesses
-
The experimental setting remains substantially more controlled than realistic synthetic-data training pipelines. The study considers only one synthetic transformation, , with source-grounded QA fine-tuning on two text domains. It does not establish whether the signal remains detectable after longer transformation chains, substantial mixing with unrelated training data, or other synthetic transformations. These conditions could significantly dilute the source-specific signal and therefore affect the practical significance of ancestral auditing.
-
Robustness to training stochasticity is insufficiently established. The paper reports one training realization per setting. Given that the proposed signal is defined through relatively small likelihood differences between members and nonmembers, it is important to know how much the reported AUC and the advantage of reference calibration vary across independent fine-tuning runs. The current source-level bootstrap quantifies uncertainty conditional on the trained models, but does not capture training-run variability. The authors explicitly acknowledge the single-realization limitation.
A secondary concern is that the comparison between direct-source scoring and sibling scoring is not fully controlled: the paper itself notes that the two approaches differ in probe format, token coverage, and query budget. Therefore, this experiment shows that the implemented sibling audit performs better, but does not cleanly establish that siblings are intrinsically more informative than directly probing the source.
Questions for authors
-
Training variability: Have you repeated target and/or reference fine-tuning with multiple random seeds? If so, how stable are STE and the Multi5 versus MSG improvements across independently trained models? This would materially affect my confidence that the measured signal is not specific to the particular training realizations used here.
-
Training-data dilution: Do you have results where synthetic descendants from the audited sources form only a small fraction of a larger mixed fine-tuning dataset? The current setup makes the source descendants a relatively direct component of the adaptation data, and it is unclear how quickly the audit signal disappears when they are diluted by unrelated examples.
-
Direct-source comparison: Since Direct-S and sibling MSG use different formats and query/token budgets, can the authors provide a budget-matched comparison? This would clarify whether the improvement is specifically due to probing regenerated siblings rather than increased or differently structured query coverage.
8 comments
(2/2) Response to Reviewer RyW2
For W1. Longer transformation chains
A new BillSum pilot retains signal through five successive stages of QA generation. With Qwen generation and a DeepSeek student, n = 1 generates QA from the source. Each later stage receives only the preceding QA, not the source, and rewrites it under a fixed prompt.
At each depth, a fresh target trains for five epochs on 2,000 QA from the same 500 members. The 1,000 evaluation sources, K = 4, L = 16, original audit QA and five references stay fixed. Only targets are retrained, starting from the pretrained base rather than continuing from the preceding target. Keeping probes and references fixed isolates the effect of changing the descendants used for target training and tests whether the original audit still detects participation. Repeated QA remain; there is no deduplication, semantic filtering or additional generation to improve a stage.
| Depth | MSG AUC | Multi5 AUC | Multi5 TPR at 5% FPR |
|---|---|---|---|
| 1 | 0.9394 | 0.9711 | 91.2% |
| 2 | 0.9351 | 0.9663 | 86.8% |
| 3 | 0.9343 | 0.9664 | 90.0% |
| 4 | 0.9314 | 0.9644 | 90.2% |
| 5 | 0.9313 | 0.9660 | 88.6% |
At n = 5, Multi5 AUC is only 0.0051 below n = 1. This tests a controlled chain of QA rewrites, not every synthetic format or a fixed amount of information loss per stage. Semantic preservation is not certified; other transformation types remain future work.
Revision: Appendix I.3, pp. 39–40, Table A46; the introduction distinguishes this pilot from the primary study at n = 1.
For Q3. Direct-S comparison with matched budgets
The sibling advantage survives matched query and token budgets across all eight students and both domains. We reuse targets and pretrained bases with Qwen as provider and auditor, without new training or fine-tuned references. Both MSG and the direct controls use base calibration, so reference training does not confound this comparison.
Each method uses 16 probes per source per model, matching the main experiment's L=16 budget. Each direct probe matches its paired sibling QA in input tokens excluding padding and scored content tokens, excluding EOS. We test raw source windows and source continuations in the Instruction/Response template. Fixed anchors and adjustments at token boundaries select windows, without labels or scores.
Values below average metrics computed separately for the eight models with Qwen as both provider and auditor, not pooled predictions. They do not average the three matched-generator conditions as the original main table does:
| Dataset | Probe | AUC | TPR at 5% FPR |
|---|---|---|---|
| Enron | Matched raw source windows | 0.7266 | 25.45% |
| Enron | Matched templated source windows | 0.6464 | 17.78% |
| Enron | Sibling MSG | 0.9103 | 53.68% |
| BillSum | Matched raw source windows | 0.7031 | 22.63% |
| BillSum | Matched templated source windows | 0.6508 | 15.60% |
| BillSum | Sibling MSG | 0.9282 | 58.93% |
MSG exceeds both controls on AUC and TPR at 5% FPR in every model and domain. More scoring queries or tokens alone therefore do not explain the advantage. The cost of QA generation and coverage of distinct facts are not matched.
Revision: Section 4.4, p. 5; Appendix E.1, pp. 22–25, Tables A19–A20. The original Direct-S results using full sources in Table 2 remain unchanged.
Thank you for the detailed response and substantial additional experiments. The new results address most of my main concerns, particularly regarding training-run variability, dilution with unrelated data, and the budget-matched direct-source comparison. The consistency across five seeds and the strong performance even at 5% source-record share are especially reassuring.
The longer-chain experiment is also useful, although it remains a controlled QA-to-QA rewriting pipeline. Thus, my main remaining reservation concerns generalization to substantially different synthetic transformations or pipelines, where the information preserved from the original source may differ considerably. In addition, the seed analysis isolates training randomness while keeping the sources and generated QA fixed, so robustness to regeneration or source/QA sampling variability is still less clear.
The rebuttal has strengthened the paper and addressed the majority of my concerns. I will read the revised manuscript and these new experiments more carefully and reconsider my score accordingly.
(1/2) Response to Reviewer RyW2
We thank the reviewer for their careful review and valuable feedback.
We have uploaded a revised PDF with changes marked in blue.
For Q1 + W2. Robustness across independent fine-tuning runs
MSG and the Multi5 advantage persist across five training seeds, eight students, and both domains. Seeds 42–46 control LoRA initialization, dropout and data order. Each new seed retrains the target and all five references; seed 42 reuses the original run. Sources, QA, memberships, reference cohorts and hyperparameters stay fixed, including the original five-epoch schedule and final-checkpoint rule. Qwen is provider and auditor, with N = 1,000, K = 4, L = 16.
The table reports AUC mean ± sample SD across five fine-tuning runs:
Multi5 improves AUC in all 80 paired evaluations, covering two domains, eight student families and five training seeds. Each evaluation uses a target and five references. AUC gains range from 0.0180 to 0.0717, with Multi5 AUC SD 0.0009–0.0041. TPR at 5% and 1% FPR also improves in all 80 comparisons, although it varies more across runs.
These experiments measure training randomness, not source or QA selection. Source bootstrap remains separate: it measures uncertainty conditional on trained models, whereas retraining measures run variability.
Revision: Section 4.9 and Table 4, p. 10; full runs in Appendix I.1, pp. 35–38, Tables A40–A43.
For Q2 + W1. Dilution by unrelated training data
Dilution weakens MSG but does not erase the signal; matched Multi5 stays close to performance without background. On both domains, we use DeepSeek with Qwen as provider and auditor. We retain the original 1,000 evaluation sources, four training QA from each of 500 members, and 16 audit QA per source. Thus, each target keeps the same 2,000 source QA while added background reduces their share. Each reference keeps its cohort, disjoint from evaluation sources, and receives the same background as the target, so calibration also accounts for adaptation to that background. The original five-epoch schedule and final checkpoint remain fixed: source QA are seen equally often, while total compute increases.
The UltraChat sweep reports AUC:
At 5% source records, response tokens from source QA, including EOS, account for only 0.373% / 0.762% on Enron/BillSum. Multi5 loses just 0.0157 / 0.0054 AUC compared with training without background and retains 77.2% / 88.0% TPR at 5% FPR.
Other backgrounds agree: 13,828 human-written Dolly records yield Multi5 AUC 0.9558 / 0.9692; 9,000 Dolly plus 9,000 UltraChat yield 0.9508 / 0.9707. A broader mixture of 3,600 records each from Dolly, UltraChat, Alpaca, SQuAD v1 and OASST1 yields 0.9484 / 0.9721 AUC, 77.8% / 91.6% TPR at 5% FPR, and source token shares 1.620% / 3.270%. All use references retrained on the same background as their target.
Revision: Section 4.9 and Figure 7, p. 10; all settings in Appendix I.2, pp. 36–39, Tables A44–A45.