- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper studies whether imposing nonnegative weights on Transformer FFNs changes sensitivity to token substitutions. For T5-small with ReLU, the resulting FFN branch is coordinatewise monotone in its own input, although the full Transformer is not monotone. The main experiment reports smaller HotFlip-induced loss increases for the constrained model, at the cost of worse clean and attacked performance. The paper also presents local Jacobian arguments, semantic-order probes, and an exploratory Pythia-1.4B study.
Critical strengths
- The authors correctly distinguish local FFN monotonicity from full-model monotonicity and explicitly acknowledge that nonnegative weights do not imply a Lipschitz or robustness guarantee. This is an important conceptual clarification and prevents several common overclaims.
- The paper consistently reports that the constrained model has worse clean quality and higher absolute attacked loss, which makes the trade-off transparent. For example, on CNN/DailyMail, ROUGE-L drops from 33.2 to 31.5, while attacked loss is 3.53 versus 3.12 for the baseline.
These are good qualities of the study, but they are not sufficient for acceptance given the issues below.
Critical weaknesses
- The constrained model is initialized approximately from , which removes all negative pretrained weight signs and therefore substantially changes the pretrained function before fine-tuning. The paper's own control indicates that an unconstrained model initialized from pretrained magnitudes reaches essentially the same validation loss as the constrained model, suggesting that destruction of the pretrained sign structure is already a major factor. Crucially, attack results for this control are unavailable. Therefore the key comparison does not tell us whether the reduced HotFlip sensitivity comes from persistent nonnegativity/monotonicity, from the initialization change, from optimization differences, or simply from obtaining a substantially worse model. This is not a minor ablation: it directly affects the interpretation of the paper's main result.
- The main T5 result is based on only one training seed and 200 examples, using a fixed-gradient HotFlip variant that does not recompute gradients after substitutions and does not even verify the final token distance after decode/re-encode. The paper also lacks paired per-example losses for statistical testing. The Pythia experiments do not resolve this concern. Pythia uses GELU, so the FFNs are not actually monotone; the constrained and baseline models receive unequal training schedules; and the attack objective scores the substituted tokens themselves. 47380_Monotone_FFNs_and_the_Qu Moreover, random substitutions damage the baseline more than the fixed-gradient HotFlip attack, which the authors themselves identify as evidence that HotFlip is a weak search procedure in this setting.
Questions for authors
- Can the authors run the same T5 attack evaluation on the unconstrained magnitude-initialized and sign-frozen controls? In my view, this is essential. If an unconstrained -initialized model shows the same reduction in attack-induced loss, the main effect cannot reasonably be attributed to persistent nonnegativity.
- Does the T5 result persist across multiple independently trained seeds under a stronger adaptive attack that recomputes gradients after each substitution and enforces the actual token-edit budget? A paired per-example evaluation would also be important. A positive result here could materially change my assessment.
I would not phrase these as optional future work; both are directly relevant to the current claims.