- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper argues that the user behavior sequences fed to sequential recommenders contain noisy and missing items, and proposes SeqEditor, a model-agnostic procedure that improves sequential recommendation through sequence editing. A Quality Assessor selects seed sequences using normalized gradient alignment with a held-out reference-user objective, averaged across auxiliary SASRec checkpoints. An LLM-based Quality Editor is trained on synthetically corrupted seeds through supervised fine-tuning and DAPO with an interest-aware reward. The editing pipeline applies denoising, directed-PMI-based predecessor insertion, and a second denoising pass. Experiments report improvements across five recommendation backbones (GRU4Rec, BERT4Rec, SASRec, TIGER, HSTU) on three Amazon datasets, together with ablations, cross-domain transfer, and efficiency analyses. The paper also provides a link to an anonymous code repository.
Critical strengths
1.The problem is relevant, and the separation between sequence editing and downstream recommendation makes the framework potentially reusable. Table 1 reports consistent improvements across both conventional and generative recommendation backbones, with five-run averages and significance tests against the corresponding unedited baselines.
2.The assessor has a coherent local-utility interpretation. Equation (5) reasonably connects normalized gradient alignment to a first-order reduction in reference loss. The interest-aware reward also provides a sensible mechanism for discouraging erroneous deletions for users with broader interests.
3.The evaluation includes useful controls beyond the main comparison: random and loss-based seed selection, single-checkpoint scoring, SFT-only editing, denoising/supplementation ablations, denoising baselines, cross-domain editor transfer, and an LLM-embedding comparison. These experiments provide meaningful evidence that the approach is practically useful.
Critical weaknesses
W1.The connection between the operational quality score and actual noise/missingness remains insufficiently established.
- Positive gradient alignment indicates local usefulness to an auxiliary model and reference distribution; it does not establish that a sequence is free of noisy interactions. Nevertheless, seed interactions are implicitly treated as clean when constructing synthetic labels. Likewise, successful recommendation after PMI-based insertion does not establish recovery of genuinely missing behavior. The ablations and Appendix C.7 support usefulness of the pipeline, but do not fully distinguish behavioral repair from task-oriented augmentation or suppression of atypical preferences. This matters because the paper repeatedly attributes its gains to resolving sequence-quality flaws.
W2. Ambiguity in Test-Time Evaluation Protocol and Prohibitive Online Inference Latency.
- Section 3.3 and Figure 2 describe editing as SeqEditor's inference stage, while Algorithm 1 (Lines 10–11) specifies editing training data. Although Section 4.5 and Figure 5 suggest editing test histories, whether this applies to the main evaluation remains unclear. If test histories are edited, is editing performed online or precomputed/cached? The pipeline requires two denoising passes, but Table 6 does not clarify whether its reported 45ms per sample covers one pass or the full pipeline, leaving serving costs uncertain. If test histories remain unedited, please clarify how Figure 5 relates to the main evaluation and discuss the potential mismatch between edited training histories and raw test inputs.
W3. Unrealistic Uniform Synthetic Noise and Noise-Free Seed Assumption.
-
In Section 3.2.1, sequences in (where ) are treated as completely clean ground truth, and only the 0 to () artificially injected items are labeled as noise . However, a positive sequence-level gradient inner product only indicates positive aggregate local training utility for the sequence as a whole and does not guarantee that every individual interaction is noise-free. Treating original noisy items inside as clean labels introduces false-negative supervision during SFT and RL.
-
More importantly, the operator in Equation (7) injects items uniformly at random from . As illustrated in Appendix Figure 7, this frequently inserts completely unrelated cross-category items (e.g., inserting a GPS/Altimeter wristwatch into a clothing sequence containing men's pajama pants and women's boots ). Consequently, the LLM can achieve high validation (Figure 6a) simply by performing trivial category-outlier detection, rather than learning to identify realistic, fine-grained noise such as within-category comparison clicks or popularity-biased accidental clicks.
W4. Context-Insensitive First-Order PMI Supplementation.
-
In Equations (13)–(17), the supplementation function inserts a predecessor item before solely based on the global pairwise transition score , completely ignoring the actual preceding item already present in .
-
Even when the existing transition is already semantically coherent, the rule in Equation (17) blindly inserts between and whenever a globally frequent predecessor exceeds . Because this operation is applied independently to every item in , it risks nearly doubling the sequence length and repeatedly injecting globally popular items.
Questions for authors
-
Q1. Test-Time Protocol and Serving Latency. During evaluation on the test set (Tables 1, 2, and 7), are the test user sequences also edited by SeqEditor () prior to next-item prediction? If yes, how can a two-pass 4B LLM pipeline (~90ms per sequence according to Table 6) be practically deployed in low-latency recommendation serving? If no (only training sequences are edited), how do you reconcile the train–test distribution discrepancy and the test-time editing shown in Figure 5?
-
Q2. Robustness to Realistic/Hard Noise Injection. How does SeqEditor perform if in Equation (7) samples harder negative items—such as popularity-sampled items or items within the same coarse category as the user's existing interactions—rather than uniform random items from ?
-
Q3. Clarification on Selection Ratio: What exact percentage of training sequences satisfy on Beauty, Sports, and Clothing respectively? Please clarify whether the Quality Editor was trained on (Section 3.1) or the top 20% subset (Appendix B.1, Equation 18).
-
Q4. Context-Aware Supplementation: In Equation (17), what is the average number of supplemented items per sequence before and after the second denoising pass? Would conditioning supplementation on the transition from the preceding item (e.g., only supplementing when is low) prevent disrupting already coherent transitions?
7 comments
Q3: Clarification on Selection Ratio.
Thank you for the question. We clarify two points: the seed ratio for Quality Editor, and the role of the top 20% in Appendix B.1.
Training seeds and selection ratio of Quality Editor. The training seeds used by Quality Editor in both SFT and RL are selected by the criterion in Section 3.1, not by a fixed top 20%. On Beauty, Sports, and Clothing, sequences satisfying this criterion account for 34.18%, 27.69%, and 31.65% of the training sequences, respectively. The denominator is the candidate training set , i.e., the training sequences after excluding the reference set.
Role of the top 20% in Appendix B.1. This rule is used only for the high- vs. low-quality comparison in Section 1 and 4.4. Specifically, we select the top and bottom 20% by score, train SASRec-HQ and SASRec-LQ, and compare the effect of sequence quality under the same data scale. This split is not used to construct Quality Editor's training data. Our manuscript reuses in both places, which may cause confusion.
We have renamed the seed set as in Sections 3.1–3.2 and Eq. (7), and added a note in Appendix B.1 clarifying that the top-20% split and is used only for the comparison experiments and is not the training seed set.
Q4: Context-Aware Supplementation.
Thank you for the question. We respond to two points: (i) the number of supplements before and after the second denoising pass; (ii) the conditional supplementation experiment.
(i) Supplemented items before and after the second denoising pass.
We count the average number of supplement items before the second denoising pass and the average number of newly added items that remain after it. The statistics cover all sequences to be edited, including those with no supplementation. After denoising, we count only the newly added items that are still kept.
As shown in Table 2, SeqEditor does not keep all supplemental items produced by Eq. (17). It first supplements items and then filters them with full context.
Table 2: Average number of supplements per sequence before and after the second denoising pass.
Dataset Before 2nd denoising: avg. supplements per sequence After 2nd denoising: avg. kept supplements per sequence Beauty 1.14 0.62 Sports 1.21 0.71 Clothing 0.91 0.58
(ii) Conditional supplementation experiment
We implement the suggested variant: supplement only when the original transition satisfies . We set , with SASRec as the backbone. Results are shown in Table 3.
Table 3. Recommendation performance under conditional item supplementation with different thresholds.
Setting Beauty (R@10 / N@10) Sports (R@10 / N@10) Clothing (R@10 / N@10) SeqEditor 0.0658 / 0.0341 0.0414 / 0.0214 0.0308 / 0.0142 Conditional, =0.2 0.0625 / 0.0330 0.0378 / 0.0203 0.0296 / 0.0137 Conditional, =0.5 0.0646 / 0.0337 0.0405 / 0.0211 0.0301 / 0.0139 Conditional, =0.8 0.0657 / 0.0343 0.0417 / 0.0213 0.0304 / 0.0140
Results show that tightening consistently lowers performance. Eq. (17) targets high recall at candidate supplementation generation, leaving precision to the second Quality Editor pass over the full context. Conditioning supplementation adds an extra hyperparameter that pre-filters candidates. This trades recall for precision: some unreasonable candidates are filtered out early, but reasonable ones removed at this stage cannot be recovered later.
We thank the reviewer for this valuable direction. This two-stage design (high recall in candidate generation, precision from the second Quality Editor pass) achieves an effectiveness–efficiency balance in our experiments.
Dear Reviewer RftV,
We hope this message finds you well.
Thank you for your insightful and constructive comments on our manuscript. They have been invaluable in helping us improve the quality and clarity of our work. We have carefully responded to each of your comments and revised the manuscript accordingly.
We would be grateful if you could kindly review our response and the revised manuscript at your earliest convenience. Please let us know if any further clarification or additional information is needed; we would be happy to provide it.
Thank you again for your time and thoughtful review. We look forward to hearing from you.
Sincerely,
The Authors
Response to Reviewer RftV
Thank you for your careful review and constructive comments; we hope our responses below resolve your concerns.