- Rating
- 2
- Confidence
- 2
- Informativeness
- 2(+1)
- Presentation
- 2
- Soundness
- 2(+1)
Read review
Paper summary
This paper introduces Fisher-IRG, a framework for analyzing local invariant representation geometry in pretrained language and vision models. The key idea is to replace covariance-based characterization of representation displacement with a Fisher-information-based geometry that measures how local representation directions affect the model’s predictive distribution. Given semantic-preserving (SP) and semantic-changing (SC) neighborhoods around an anchor, the method aggregates local Fisher operators for the two types of variations and solves a regularized generalized eigenvalue problem to identify directions that are more predictive-sensitive to semantic changes than to meaning-preserving variations.
Critical strengths
- The motivation is interesting, although it could be further strengthened.
- The work addresses a fundamental representation-analysis problem while making an effort to connect with modern large language and vision models.
- The empirical evaluation covers multiple models and several validation aspects.
Critical weaknesses
- The primary evaluation criterion is closely aligned with the objective used to construct the Fisher-IRG subspace. Since Fisher-IRG explicitly selects directions according to predictive sensitivity to semantic-changing versus semantic-preserving variation, evaluating the resulting subspace using the same predictive KL-based criterion provides limited independent evidence of its superiority over Cov-IRG.
- The methodological novelty appears limited. The proposed framework largely follows the existing covariance-based invariant representation analysis paradigm, while replacing covariance-based representation geometry with a Fisher-based predictive geometry and retaining a similar generalized eigenvalue formulation. Although this replacement is conceptually reasonable, the paper does not sufficiently demonstrate that it constitutes a substantial methodological advance. Moreover, the improvements on more independent evaluations, such as held-out semantic retrieval, are relatively modest, making the practical benefit of the added complexity less compelling.
- The validity of the semantic-preserving / semantic-changing neighborhoods is insufficiently justified. The entire framework relies heavily on the assumption that the constructed SP and SC variants cleanly isolate meaning-preserving and meaning-changing variations. However, the paper provides limited independent validation that these variants are free from confounding factors such as lexical choice, syntax, sentence structure, visual appearance, or other low-level cues. Since the Fisher operator directly measures predictive sensitivity, such confounds could substantially influence the recovered subspaces. Stronger human validation or confound-controlled experiments would be necessary to support the claim that the discovered geometry genuinely reflects semantic structure.
- The empirical evaluation is largely confined to synthetic or tightly controlled local semantic neighborhoods constructed specifically for this analysis. While this setup is useful for isolating the proposed geometric effect, it remains unclear whether Fisher-IRG provides meaningful benefits on realistic downstream representation-learning or semantic understanding tasks.
- The paper suffers from significant presentation and visualization issues. For example, Fig. 1 is visually cluttered and does not clearly convey the key methodological intuition. The overall formatting and visual presentation of the manuscript could also be substantially improved.
Questions for authors
See the weaknesses above, especially 1-4.
6 comments
W2. Methodological novelty: Is Fisher-IRG merely covariance replacement in an existing generalized eigenproblem?
The novelty is not the Fisher matrix or the generalized eigenproblem individually, but their integration into a contrastive framework for discovering local predictive-selective representation subspaces. We have revised the introduction and contributions to make this distinction explicit.
Our contribution follows three connected steps.
First, we establish the motivating geometric phenomenon. Controlled distance-matched SP/SC experiments show that comparable Euclidean displacements can have substantially different predictive consequences. This establishes an existence claim: displacement magnitude alone does not always determine the behavioral significance of representation variation.
Second, we formulate a different object of geometric measurement and make it computationally operational. Cov-IRG analyzes the directional covariance of sampled representation displacements. Fisher-IRG instead measures local predictive sensitivity through the second-order KL geometry,
We evaluate Fisher forms at individual SP and SC neighborhood representations, aggregate them separately, and discover directions through the contrastive generalized eigenproblem
First-order score computation, top- output approximation, and low-rank eigendecomposition make this construction feasible for large pretrained models. The approach does not assume that finite anchor-to-variant displacements are infinitesimal tangent vectors.
Third, we establish that this geometric change has measurable consequences across modalities. Across seven language and three vision models, Fisher-IRG exhibits stronger predictive selectivity and generally greater Grassmann reproducibility than Cov-IRG. More importantly, the two methods recover substantially different local subspaces:
| Geometric comparison | Observed result |
|---|---|
| Fisher–Cov projection distance | 0.992–0.998 |
| Mean principal cosine | 0.056–0.080 |
| Cross-method separation exceeding within-method variability | 100% of evaluated semantic groups |
These findings establish that the Fisher and covariance constructions do not merely yield different numerical estimates of the same subspace. They select different directions because they measure different geometric quantities. Near-orthogonality alone does not prove semantic superiority; the causal interventions and held-out semantic evaluations provide the complementary functional evidence.
We do not claim to invent Fisher–Rao geometry or generalized eigendecomposition. Our methodological contribution is a theoretically grounded and computationally practical framework for contrastive local predictive geometry, with empirical characterization across language and vision.
Manuscript Change: Revised abstract and Section 1 contributions; Sections 3.1–3.2; Section 4.2, Displacement magnitude does not uniquely determine predictive consequence; Section 4.4; Appendix B and Appendix E, Table 20.
W3. Semantic-neighborhood validity and possible confounds
We agree that the SP/SC construction is central to the semantic interpretation of the recovered geometry. We have expanded Appendix A to document how variants are generated, screened, and partitioned, and added two validation experiments.
For language, we construct 1,800 neighborhoods using semantically constrained generation with ChatGPT and Claude. Each contains 10 SP and 64 SC variants. For vision, we construct 1,000 Visual Genome neighborhoods, using appearance transformations for SP and localized object edits with GroundingDINO, SAM, and Stable Diffusion inpainting for SC. Generated variants underwent manual quality screening.
We further conducted an AI-assisted semantic-label audit of 200 randomly sampled language variants:
| Assigned label | Confirmed | Ambiguous | Incorrect |
|---|---|---|---|
| SP (100) | 81 | 14 | 5 |
| SC (100) | 85 | 9 | 6 |
| Total (200) | 166 | 23 | 11 |
The overall confirmation rate is 83%. This is not an independent human annotation study, and we explicitly acknowledge the remaining ambiguity rather than assuming perfectly controlled labels.
To directly test lexical confounding, we evaluated 200 held-out groups in which SC variants are lexically closer to the anchor than SP variants, reversing the usual relationship between surface similarity and semantic consistency.
| Representation | Pairwise accuracy ↑ | Semantic separation ↑ |
|---|---|---|
| Original | 0.71 | 0.011 |
| PCA | 0.78 | 0.023 |
| cPCA | 0.74 | 0.018 |
| Cov-IRG | 0.81 | 0.029 |
| Fisher-IRG | 0.86 | 0.037 |
Fisher-IRG retains the strongest discrimination under this control, suggesting that its semantic selectivity cannot be explained solely by lexical overlap. Nevertheless, other potential confounds, including syntax and visual appearance, are not completely eliminated.
Manuscript Change: Appendix A, dataset generation, quality control, and discovery/evaluation separation; Appendix A.1, Semantic Neighborhood Validity and Confound Controls, Tables 10–11; Section 4.6; Appendix I.
W4. Generalization beyond synthetic neighborhoods and practical utility
We agree that a foundational geometric analysis should be distinguished from a complete downstream application benchmark. We have expanded the functional evaluation beyond the original controlled neighborhoods to examine whether the recovered subspaces retain useful information under more natural conditions.
Natural language variation (SNLI). We evaluate Mistral-7B and LLaMA-3-8B on naturally collected entailment and contradiction pairs. Fisher subspaces are estimated from the original synthetic discovery data and transferred without using SNLI labels for subspace estimation.
| Model | Original | Cov-IRG | Fisher-IRG |
|---|---|---|---|
| Mistral-7B pairwise accuracy | 0.6467 | 0.6467 | 0.6833 |
| LLaMA-3-8B pairwise accuracy | 0.5800 | 0.6600 | 0.6967 |
Both experiments use compact 16-dimensional Fisher-derived representations rather than the original full-dimensional features.
Visual corruption retrieval. We also evaluate 600 corrupted-image queries from 200 Visual Genome images, applying Gaussian noise, defocus blur, and JPEG compression at severity 3.
| Representation | Hit@1 ↑ | MRR ↑ |
|---|---|---|
| Original | 0.990 | 0.995 |
| cPCA | 0.445 | 0.556 |
| Cov-IRG | 0.420 | 0.549 |
| Fisher-IRG | 0.530 | 0.624 |
The original full-dimensional representation remains substantially better than the compressed representations. The relevant finding is therefore better preservation of retrieval utility under dimensionality constraints, not superiority over the original features.
Together with the representation-intervention results, these experiments establish functional relevance beyond KL-based selectivity and the original generated evaluation variants. They do not constitute state-of-the-art application benchmarks.
Our primary contribution is to establish and characterize a local predictive geometry; developing task-specific retrieval, steering, robustness, or disentanglement applications is a separate research direction that builds on this foundation.
Manuscript Change: Section 4.5–4.6; Appendix F.1, extended causal interventions; Appendix G.3, SNLI evaluation and Figure 5; Appendix G.4, visual retrieval and Figure 6; Appendix I, Functional validation and potential applications.
We thank the reviewer for recognizing the importance of the representation-analysis problem and the breadth of our language and vision evaluations. We appreciate the concerns regarding methodological novelty, evaluation independence, semantic-neighborhood validity, and practical utility. In response, we have substantially clarified the contributions and their theoretical scope, added independent semantic evaluations, and expanded the evidence for neighborhood validity and functional relevance. We address the concerns individually below.
W1. Evaluation circularity: Does the predictive-KL criterion provide independent evidence?
We agree that KL-based selectivity is aligned with the Fisher discovery objective and should not, by itself, establish semantic superiority. We have clarified the distinct roles of our evaluations and strengthened the evidence using criteria that are not optimized during Fisher subspace discovery.
In particular, the experiments establish different properties:
The third category provides more independent functional evidence. Fisher-IRG achieves the largest held-out semantic separation margin in 21/21 language model–layer comparisons and 9/9 vision layer–difficulty comparisons. In seven-model semantic retrieval, its macro-average pairwise accuracy improves from 0.949 to 0.959, while Hit@1 improves from 0.873 to 0.885 relative to the original representations.
We additionally introduced paired bootstrap analyses with 2,000 replicates. The 95% confidence intervals for the aggregate improvements exclude zero, although several individual-model comparisons remain statistically inconclusive.
To further reduce dependence on the original generated neighborhoods, we added semantic matching on SNLI, transferring Fisher-derived subspaces learned from synthetic discovery data without re-estimation on SNLI labels, as well as instance retrieval under visual corruptions. These provide additional evidence under independently defined semantic or instance-matching criteria.
We therefore interpret KL-based selectivity as validation of the intended predictive geometry, while treating cosine-based discrimination and retrieval as complementary evidence of semantic utility.
Manuscript Change: Sections 4.3–4.6; Appendix G.1, Statistical Reliability of Semantic Retrieval, Tables 28–29; Appendix G.3–G.4, natural semantic and visual retrieval evaluations; Appendix I.