- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The task is conventional LLM personalization, with a shared model and in-context user history. The paper proposes MIRROR, which follows mostly standard on-policy self-distillation, where the users' Y serve as additional privileged content in the teacher's context. A symmetric JSD loss is used for distillation. The paper also proposes MIRROR-F, a variant that additionally adds a teacher-forced NLL term on a small set of reference tokens. The reference tokens are chosen by format rules and filtered to words that also appear in the input. The methods are evaluated primarily on LaMP with Qwen3 1.7B and 4B.
Critical strengths
-
The formulation is simple and practical: on-policy self-distillation is conceptually a good fit for the personalization task.
-
The evaluation covers out-of-distribution forgetting, with positive results.
Critical weaknesses
-
It is unclear where the performance improvements come from. Although MIRROR is simple and principled, it seems to have limited performance gain without the additional token selector and NLL loss in MIRROR-F. But the token selector in MIRROR-F is a rather hard-engineered heuristic with little principled justification behind it. The absence of an ablation of α = 0 or 1 makes this more concerning.
-
Experiments are not entirely well controlled. No confidence interval is included. And the tuning procedure for baselines is under-specified; several baselines score below Base in Table 1. Only one LLM family is used, at a rather small scale, and the judge is from the same family.
-
The OOD experiment could be biased. The OOD experiment is evaluated with a metric that rewards the smallest deviation from Base, which systematically favors the self-distillation-based method like MIRROR.
Questions for authors
Please see the weaknesses above.
Address the issues raised by Reviewer 3 and detail the revisions made to the paper.[Check Revised Paper for details]
We thank the reviewer for the encouraging assessment and the precise concerns. Each point gives the result table and where we revised.
W1 - Where do the gains come from? alpha=0/1 ablation; the heuristic selector. (Revised: single clean ablation, Table 3; selector analysis in Appendix A.5 and the new extensibility discussion in Appendix on focal token selection.) Built up from MIRROR (G-Eval / IC on Abstract):
Removing the frozen teacher or the on-policy term (alpha=1) each collapses the model, so both core components are necessary; the selective anchor adds IC at near-unchanged quality and beats uniform anchoring on IC in 9/9 settings. The selector is deliberately white-box and user-editable; we added a discussion of its industrial extensibility (domain-specific definitions of salient content) in the appendix.
W2 - Confidence intervals; baseline tuning; single family; same-family judge. (Revised: Appendix A.4, A.8; added Qwen2.5-3B and gemma-2-9b.) All trained methods share one tuning budget (Appendix A.4). We added a second model family and a second-family judge; conclusions hold (per-setting 95% intervals in Table 14; Spearman 0.86-1.00). A third backbone family beyond Qwen would require retraining all methods on all tasks and is time-prohibitive under our present compute budget; we will add it with more compute.
W3 - The OOD metric may favor self-distillation by rewarding small deviation from Base. (Revised: OOD now a table, Table 2; full per-metric Table 17.) Signed worst-case change vs. Base (smaller of ROUGE-1/METEOR, averaged over 3 OOD tasks; positive = better than Base):
(Full 9x3-task grid in Table 2.) MIRROR/MIRROR-F never lose more than 10% on any of the nine settings, whereas every imitation baseline loses 48-65% in at least one - a large-margin gap, not a metric artifact; positive entries show the metric does not penalize improvements over Base.
We are grateful for the constructive review and happy to add any further clarification.