- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes ARSO, a weight-only post-training quantization method that combines scale optimization, reconstruction-aware rounding, and sequential compensation to improve quantization accuracy. Experiments on LLaMA and Qwen models across 2-4 bits demonstrate improved perplexity and zero-shot accuracy over some existing baselines.
Critical strengths
- This paper reports strong improvements across multiple LLaMA and Qwen models, with particularly substantial gains at 2 bits. The ablations also provide some evidence that the proposed components contribute to the overall result.
- This paper present a coherent sequential quantization procedure. ARSO improves quantization accuracy without introducing additional inference-time overhead, while requiring only about 2$\times$ the quantization time of GPTQ. This makes the approach practical for LLM deployment.
Critical weaknesses
- The claimed contributions are not new, and the relationship to closely related prior work is insufficiently established. First, the proposed SO is essentially the same optimization problem considered in "Two-Stage Grid Optimization for Group-wise Quantization of LLMs" (ICASSP 2026). The latter solves it through closed-form coordinate-descent updates, whereas ARSO formulates the corresponding normal equations. These are different solution procedures for the same quadratic objective rather than fundamentally different optimization formulations. Second, the proposed AR in Section 3.2.2 relies on the Schur-complement conditional curvature obtained by eliminating the optimal future compensation variables. This has already been explicitly developed in STLA (ICML 2026), and should not be presented as a contribution. Neither work is cited or discussed, raising serious concerns about the originality of the paper's core contributions.
- The experiments omit comparisons with these closely related methods. Moreover, the ablation results suggest that most improvements come from SO, while the additional gains from AR and J-SO are relatively modest, making it difficult to establish the value of the remaining novel components.
Questions for authors
- How J-SO differs from the group-scale refinement with fixed integer codes in "Two-Stage Grid Optimization for Group-wise Quantization of LLMs" (ICASSP 2026).
- Can the authors clarify how ARSO’s reconstruction-aware rounding relates to "STLA: Spatiotemporal Lookahead Alignment for Post-Training Quantization" (ICML 2026), particularly their use of a Schur-complement objective to account for future weight compensation?
- Can the authors provide comparisons with these closely related methods under matched experimental settings?
- Can the authors explain when repeatedly re-optimizing the processed-prefix scales is expected to help, and whether the reported gains depend on performing these updates during sequential quantization rather than after it?