- Rating
- 2
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies how field legibility and inference context affect memorization in document VLMs. The authors introduce Visual Canaries, synthetic documents containing identifier secret pairs, together with CMMG, a paired metric that compares fine-tuned models against matched no canary controls. Controlled experiments on three VLM backbones show that reducing a field’s legibility increases detectable memorization when the secret is part of the supervised training target. With model weights held fixed, showing the model the page a secret was paired with during training can substantially improve its retrieval, even when that page does not contain the secret itself. These results expose the limits of text only memorization audits and underscore the role of inference context.
Critical strengths
-
The rendering intervention changes only the secret field while holding the training target, exposure, page geometry, and visual token count fixed. Combined with the matched controls and the corruption, duplication, and cross backbone experiments, this makes a convincing case that field level visual degradation affects detectable memorization.
-
The fixed weight experiments were the most interesting part. An association that text only probing completely misses becomes recoverable once the model sees the page it was paired with during training. The matched controls, alternative contexts, and generation based extraction make this more convincing than likelihood scores alone.
Critical weaknesses
-
The experiments do not cleanly separate memorization from retrieval accessibility. The second experiment shows that retrieval varies sharply with inference context under fixed weights, so the higher CMMG under reduced legibility may reflect easier access to a stored association rather than more storage. The remaining gap between the corruption and font size conditions at similar transcription accuracy also suggests that legibility alone does not explain the effect.
-
The practical relevance of the context dependent extraction is limited. The strongest results depend on an artificial pairing with another canary's document, knowledge of the exact page and caption format, and assistant prefill access, while ordinary user turn prompts work much less well. Since removing the donor page's own secret eliminates retrieval, the model may have learned a narrow identifier keyed association rather than general context dependent recall, and the few training seeds further limit the precision of the reported rates.
Questions for authors
-
How can the authors distinguish increased information storage from increased accessibility under the chosen readout? Would the legibility dependent ordering persist across a broader set of inference contexts and prompt formats, rather than primarily the training style text prefix?
-
Since removing the donor page's own secret eliminates retrieval, could the authors clarify whether this high entropy field acts as the effective retrieval key? Would the same context dependent recovery occur when the paired document contains no other unique secret?
-
How well does the page conditioned retrieval effect generalize to more realistic document fine-tuning, where the paired page is not deliberately mismatched and an auditor may not know the exact training page association?