- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper uses relative representations to train linear probes that predict properties of model behavior. Empirically, the authors show that these probes can transfer across models, related datasets, and model updates without retraining, suggesting that behaviorally relevant information is organized in compatible ways across different models.
Critical strengths
-
Evidence of cross-model compatibility in behavioral representations. The authors provide empirical evidence that behaviorally relevant information is organized in compatible ways across different models, as demonstrated by the transferability of probes trained on relative representations.
-
Extensive empirical evaluation. The paper evaluates the proposed approach across different models, tasks, and settings, including cross-model transfer, cross-dataset transfer, and model updates, helping establish its applicability and limitations.
Critical weaknesses
-
Limited methodological novelty. The proposed method largely builds on existing relative representation and linear probing techniques, with the main technical additions being all-layer aggregation. While applying these techniques to cross-model behavioral monitoring is interesting, the methodological novelty appears relatively limited, and the main contribution lies in the empirical evaluation.
-
Missing all-layer Standard baseline for Online MATH. The main experiments compare single-layer Standard probes (at relative depth 0.8) against Global Anchored probes that aggregate information across all layers. Although the authors provide all-layer Standard baselines for Trivia and Guard Distillation in appendix, I could not find the corresponding comparison for Online MATH. Given that Global Anchored outperforms Standard by 3.9 AUROC points on MATH-500 in the same-model setting, including this baseline would help determine whether the improvement comes from relative representations or from concatenating representations across all layers rather than using a single layer.
-
Organization of experimental results. The experimental results section is somewhat difficult to follow due to the large number of evaluation settings and comparisons. Some important baselines and ablations are also scattered across the appendix, making it harder to assess the main experimental findings.
-
Minor presentation issues.
- Figure 1 is not explicitly referenced in the introduction, although it provides an overview of the proposed method.
- Line 38 contains the duplicated phrase "introduce relative representations".
Questions for authors
-
Choice of representation extraction protocol. The representation extraction protocols differ across the three settings: Trivia uses the final prompt token before generation, Guard Distillation averages over completion tokens, and Online MATH averages over generated tokens up to a fixed checkpoint. Could the authors elaborate on the motivation behind these choices and whether the results are sensitive to the extraction protocol?
-
Selection of regularization strength. Is the regularization strength independently tuned for Standard and Anchored probes? Given the substantial differences in feature dimensionality, independently tuning for each probe type could help ensure a fair comparison.
We thank the reviewer for their thoughtful feedback.
Novelty. The contribution is indeed new empirical evidence that independently trained LLMs encode information about their own behavior compatibly enough to reuse a frozen monitor. Prior work transferred encoder classifiers (Moschella et al.; Maiorca et al., 2023), while Chen et al. (2025) used affine maps to transfer probes for input-text properties within model families. We test whether compatibility extends to target behavior across families using anchored probe transfer. This is also a stronger test, because we do not learn a mapping between models.
This tests the behavioral side of the Platonic Representation Hypothesis (Huh et al., 2024): whether representational convergence includes information about model-specific behavior. The findings also connect representation alignment with transferable white-box monitoring. We believe these results to be valuable to the community.
Practically, this we find that probes can be reused across model changes without target labels, enabling cross-model monitoring. We now also extend Maiorca et al.'s encoder-classifier transfer to behavioral probes using Procrustes. This provides additional evidence of compatibility through a fitted map (E.2).
All-layer Standard for Online MATH. Thank you for pointing out this omission. We have added this probe in our revision. Same-model MATH-500 AUROC is:
All-layer Standard remains close to single-layer Standard, while Global Anchored achieves higher AUROC. See 4.1 and D.2 for details.
Q1. Extraction protocol. In trivia, the final prompt state is used to predict the next answer token, making it a natural pre-answer probe input. Guard labels the whole completion, so we average completion-token representations to summarize the labeled text. For online MATH, averaging only the generated prefix summarizes the reasoning available when we want to monitor. Mean pooling gives a fixed-size input, and is a standard approach in the literature.
With Guard completion activations fixed, changing anchors from final prompt states to mean completions changes calibrated transfer by at most 2.7 AUROC points (App. C.5). MATH transfer is similar at 64, 128, and 256 tokens (D.1). Transfer therefore seems stable under a variety of anchor and checkpoint choices.
Q2. Regularization strength. MATH already selects C independently for each probe from {0.01, 0.1, 1, 10, 100}. To strengthen the Standard comparison on trivia and Guard, the revised main tables select Standard's C on validation using the same grid; Anchored retains fixed C, which favors Standard. Standard AUROC increases by at most 0.7 points, and Anchored remains within 1.6 points of Standard on every trivia and Guard dataset. See App. A.5 for details.
Organization and minor issues. Sec. 4 now introduces the questions and comparisons before the results. 4.2 includes the raw-coordinate baseline and few-label curves, as well as the Procrustes baseline. Fig. 1 is referenced in the introduction, and the duplicated phrase is removed.
We would ask the reviewer to please share any remaining concerns, which we are happy to address. If the revisions resolve their concerns, we would ask them to please consider raising their score.