- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper asks whether an activation-steering vector built on a full-precision model remains behaviorally compatible with the same model after post-training quantization, with the layer, vector, and strength held fixed, and answers it negatively. The authors investigate the theoretical reasons behind the failure and present experimental results supporting the theoretical reasoning.
Critical strengths
The coverage-injection experiment (Table 3) is the strong part of the paper. It goes beyond correlation (Table 2) to a direction-specific causal manipulation, and the effect is large on that specific layer (-% error reduction) and monotone in . This validates the main theoretical idea of the paper.
Critical weaknesses
- GPTQ quantization is a well-known method. Layer-level bound in Eq. 1 is one line application of Cauchy–Schwarz. It involves the inverse of the second-moment matrix of the calibration inputs that capture how much the activations vary in each direction. Hence, if calibration data varies a lot along a test direction, then the error is small in that direction. This already explains the main mechanism of the paper without further analysis.
- Paper's central contribution is the coverage-injection experiment based on Eq. 11. The change due to "effective added synthetic data" to the objective is: Hence, injecting coverage adds a penalty on exactly the quantity being measured. It would be surprising if the error did not drop. Hence, the result in Table 3 is totally expected; it has no novelty.
- How calibration-data choice affects downstream performance after quantization and pruning is studied in arxiv: 2311.09755, arxiv: 2604.24008. Applying similar ideas to steering directions is a contribution of the present paper.
- is never formally defined. Sec. 3.1 calls ``the subspace of feasible local quantization errors,'' but the actual span of feasible errors in a large LLM model is plausibly the whole parameter space. Without it, Theorem 3.2 does not predict anything.
- Appendix B is titled Proof of Proposition 4.1 while the main text numbers it 3.1; Appendix C is Proof of Theorem 4.2 for Theorem 3.2; the Reproducibility Statement says Proofs are provided in Section 4, but Section 4 contains no proofs.
Questions for authors
See weaknesses.
3 comments
Rebuttal to Reviewer (2/2)
W4. To obtain a concrete local prediction from the theorem, the perturbation subspace must be specified. Our phrase ``the subspace of feasible local quantization errors'' was imprecise; we will instead define as an explicitly constructed linear subspace of parameter perturbations. It is not intended to denote the span of all errors that GPTQ could possibly produce. For a fixed quantized checkpoint with error , our experiment constructs . Provided , the theorem then gives the concrete local prediction as . We test this prediction along : at , predicted versus measured steered-to-unsteered KL ratios are 1.375 v.s. 1.383 for Llama, 2.096 v.s. 2.130 for Mistral, and 2.060 v.s. 2.071 for Qwen. This does not certify arbitrary GPTQ errors or global steering behavior; it validates the theorem as a local diagnostic on the stated, explicitly constructed slice. The uniform statement additionally requires positive ordinary Fisher curvature, finite amplification, and uniform remainder control on the chosen .
W5. I appreciate that you pointed out the mistakes. The appendix titles should refer to Proposition 3.1 and Theorem 3.2, not 4.1 and 4.2. We will also correct the Reproducibility Statement: Proofs are provided in Section 3, Appendix B, and Appendix C.
We modify the paper based on above comments, and we kindly ask the reviewer to reconsider the evaluation.
Rebuttal Follow-up
Dear Reviewer,
As the discussion period is about to end, we would greatly appreciate it if you could respond to our rebuttal and reconsider your evaluation in light of our response.
Best regards, Authors
Rebuttal to Reviewer (1/2)
We appreciate the reviewer's careful feedback.
W1. Eq. 1 does not explain the paper's main finding: whether an existing, fixed steering interface remains compatible after quantization. It characterizes a local coverage effect, whereas steering compatibility is an end-to-end property. Indeed, Table 3 directly shows that a coverage-only account is insufficientt: target coverage reduces local directional error by 92--98%, yet response error is unchanged for Llama (.0083 to .0083), worsens for Mistral (.0146 to .0208), and improves only marginally for Qwen (.0375 to .0365). Thus, calibration covariance identifies a necessary local mechanism, but not the downstream intervention-dependent amplification that determines whether the fixed interface is preserved. Our relative-Fisher analysis addresses this remaining mechanism, and the interpolation experiment tests its local prediction. Eq. 1 identifies the direction-specific vulnerability sΓ(d) for the effective intervention direction; we test its ranking prediction over 12 model--layer pairs, at 3 and 4 bits, with RTN as a calibration-geometry negative control. The full inverse-covariance score also outperforms diagonal, inverse-variance, norm-only, and cosine controls. The two-level analysis therefore separates calibration coverage from downstream intervention-dependent sensitivity; the former alone does not explain the whole-model findings.
W2. Eq. 11 predicts a reduction in local target-direction error; this is precisely why coverage injection is a controlled causal test rather than a proposed calibration algorithm. Its result is not merely that the targeted local quantity falls, but that this large local improvement is insufficient to preserve the fixed steering interface. Target coverage reduces local directional error by 92--98%, while response error is unchanged for Llama (.0083 to .0083), worsens for Mistral (.0146 to .0208), and improves only marginally for Qwen (.0375 to .0365). Thus, the experiment rejects the stronger coverage-only explanation: even when the predicted local mechanism is manipulated successfully, downstream intervention-dependent amplification still determines end-to-end compatibility. For Γα=Γ0+λddT, the reconstruction proxy contains the additional term λ∥δd∥2, but this does not guarantee the realized solution of discrete, groupwise GPTQ or establish direction selectivity. We test both: target and orthogonal coverage have complementary direction-specific effects over three model families and three layers, and the local reduction grows monotonically with α.
W3. Thank you for pointing us to these relevant works. We will add them to the related-work discussion. These works show that calibration-data choice can improve conventional PTQ quality through calibration-data selection or coverage. Building on this observation, we study the fixed-interface question: whether an existing FP16 steering interface remains usable after quantization when its layer, residual-stream vector, and strength are held fixed. This requires evaluating the same internal intervention rather than ordinary task accuracy or post-hoc retuning. We directly test whether an intervention-aware calibration-data selection resolves this question. In the controlled Llama mixed-calibration GPTQ comparison, half of the calibration stream contains Safety-intervened activations:
Thus, calibration-data selection can improve a direction-specific distributional metric, but selection alone is insufficient for our fixed-interface objective: it leaves Safety response error unchanged and worsens Persona steered KL. The layer-coverage experiment, relative-Fisher condition, and steering-free recovery evaluation jointly characterize this local-to-end-to-end gap, including whether ordinary output matching without steering vectors or intervened targets can recover an unseen intervention response.