- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes ScoreCBM, which uses a Label-Free CBM like approach, but with explicitly using LLMs to generate a semantic prior that guides the first process of the grounding of images to concepts. This prior is then later also used by the classifier, that uses this knowledge as a regularization. The motivation is to reduce concepts, that are semantically not needed in an explanation of a CBM, which has been proven in the past, that CBMs use concepts that are not necessarily useful.
Critical strengths
- While LLMs have been widely used in the CBM literature for concept proposal [1], using their semantic knowledge to mitigate spurrious correlations is novel. The ablation shows, that all of the two stages actually improve the overall performance (Table 4) and the general idea of the CBM approach is sound.
- You test a bunch of different datasets, explicitly separating in small, and large scale datasets. Also the fact that you not only compare your approach against LF-CBM but several different CBM works is nice.
[1] What’s in the Bottle? A Survey and Roadmap of Concept Bottleneck Models, Knab et. al., TMLR 2026
Critical weaknesses
-
Clarity of the method: If the reader does not really know the LF-CBM paper, your problem setup and preliminaries are not easy to follow. E.g., you never motivate , that is part of A bold, or generally why LF-CBM trains a projector with weights and why this is particularly useful for your case. Also, all before of this, it would have helped me to know how you generate your concepts before you start the learning process, right now, you only mention that they exist.
-
Evaluation: The major issue I see right now is the evaluation. Your whole idea is motivated by using the semantic prior of LLMs. However, In the main paper, as well as in the appendix, you only sparsely discuss the characteristics of using different LLMs within your method. Your paper would greatly profit to analyze (i) How differs the semantic prior with different LLMs (in terms of concept agreement by different LLMs) (ii) a full performance evaluation with different LLMs on all datasets, not just one. (iii) Also, since you filter concept for deduplication before you feed them to the LLM, testing how different CLIP models result in deduplication removal would also be interesting. (iv) Next what is not mentioned in the paper, why did you choose different hyperparams for each dataset (Table 7), I would have expected to see a table with results where all share the same configuration. (v) A lot of ablations are focused on one dataset, more datasets would give the results more support. However, one hint, you have already some other relevant experiments in the paper, I would have liked it if you would have already referenced them in the main paper.
Questions for authors
- You said that LLMScore for does not measure whether a concept is visually observable? I am not sure if this is problematic, since then it might be possible that ScoreCBM learns to assign concepts, the LLM has associated with the class, which are not even there, thus this might harm interpretability.
- In your LLMScore prompt, what happens with the case if the LLM returns that a feature is unclear, are you simply treating the score as 0, or do you make sth with it during the process not mentioned in the text? Otherwise, an investigation of these features would have been insightful (see A.2)
- in Appendix B.2, I think it is relevant to calculate an LLM agreement of Gemini and Qwen2.5, so if they have a similar prior, and if this can be used to explain the difference in accuracy. In addition, just the evaluation on just one dataset is in my opinion not enough. You can even think about moving this part later into the main paper with more experiments, since i think it is important to ablate your method design. - A nice baseline would have been using the binary states of the LLM produced prior to directly train a CBM, to see how large the gap between binary states, and clip refined states actually is.
- Can you explain why with a corruption ratio of 80% the performance is still that high? You slightly discussed it in the appendix, but this raises questions if this behavior is even wanted. Could you also tell the performance with , or even ?
5 comments
(iii) Sensitivity of concept deduplication to CLIP models.
We thank the reviewer for this suggestion. We conducted an additional analysis on BAR and Stanford40 to investigate how different CLIP text encoders affect concept filtering and deduplication.
Experimental setup. ScoreCBM follows the concept filtering and deduplication procedure of the original LF-CBM framework. The procedure combines MPNet and CLIP cosine similarities:
$ s(c_i,c_j)=0.25s_{\mathrm{MPNet}}(c_i,c_j)+0.75s_{\mathrm{CLIP}}(c_i,c_j). $
We fixed the original candidate concept lists, MPNet encoder, filtering rules, and similarity thresholds, varying only the CLIP text encoder among ViT-B/16 (default), RN50, and ViT-L/14. The class-name similarity threshold was 0.85 for both datasets, while the concept deduplication thresholds were 0.90 for BAR and 0.85 for Stanford40. The default ViT-B/16 setting exactly reproduced the concept vocabularies used in our main experiments.
Results. The table below reports the number of concepts retained at each stage of preprocessing.
| Dataset | CLIP encoder | Initial | After length filtering | After class-name filtering | Removed by deduplication | Final retained |
|---|---|---|---|---|---|---|
| BAR | ViT-B/16 | 308 | 234 | 233 | 13 | 220 |
| BAR | RN50 | 308 | 234 | 233 | 10 | 223 |
| BAR | ViT-L/14 | 308 | 234 | 234 | 9 | 225 |
| Stanford40 | ViT-B/16 | 2,256 | 2,208 | 2,202 | 562 | 1,640 |
| Stanford40 | RN50 | 2,256 | 2,208 | 2,205 | 453 | 1,752 |
| Stanford40 | ViT-L/14 | 2,256 | 2,208 | 2,207 | 305 | 1,902 |
Discussion. On BAR, the retained vocabulary varies only slightly across encoders (220–225 concepts). On Stanford40, the differences are more pronounced, with RN50 and ViT-L/14 retaining 112 (+6.83%) and 262 (+15.98%) more concepts than the default ViT-B/16, respectively.
These results show that the sensitivity of concept deduplication to CLIP encoder choice varies across datasets. In particular, different encoders can produce different vocabulary sizes under fixed similarity thresholds. Since this preprocessing procedure is inherited from LF-CBM rather than introduced by ScoreCBM, the analysis characterizes an existing component of the concept vocabulary construction pipeline. We have included this analysis in Appendix C.5 of the revised manuscript.
(iv) Dataset-specific vs. Shared Hyperparameters
We thank the reviewer for this suggestion. The dataset-specific settings in Table 9 (Appendix A.4) of the revised manuscript reflect differences in dataset characteristics and training configurations. To examine whether these choices are essential to the reported performance, we additionally evaluate a shared set of core hyperparameters.
We transferred the attenuation and adaptive-regularization hyperparameters selected on BAR, including the regularization strength, to five other datasets without further tuning. Dataset-dependent backbones, concept vocabularies, and CLIP filtering cutoffs were retained, while the core method-specific hyperparameters were kept identical across datasets.
| Dataset | Dataset-specific ACC (%) | Shared ACC (%) | ΔACC (pp) |
|---|---|---|---|
| CIFAR-10 | 88.55 ± 0.09 | 87.74 ± 0.02 | −0.81 |
| CIFAR-100 | 69.21 ± 0.10 | 68.89 ± 0.10 | −0.32 |
| Stanford40 | 89.55 ± 0.17 | 89.37 ± 0.10 | −0.18 |
| CUB-200 | 75.42 ± 0.05 | 75.41 ± 0.20 | −0.01 |
| Waterbirds-Species | 62.05 ± 0.08 | 62.04 ± 0.11 | −0.01 |
All results are reported as mean ± standard deviation. ΔACC denotes the change from the dataset-specific configuration in percentage points.
The shared configuration yields accuracy drops of at most 0.81 percentage points across all five datasets. Notably, ScoreCBM retains exactly the same ranking among CBM baselines as under dataset-specific tuning, ranking first on CIFAR-10, CIFAR-100, and Waterbirds-Species, and second on Stanford40 and CUB-200. These results suggest that ScoreCBM's competitive performance does not rely heavily on dataset-specific tuning of its core hyperparameters.
We have included this shared-configuration evaluation in Appendix B.7 of the revised manuscript.
(v) Ablation studies across datasets.
We agree that evaluating key design choices across multiple datasets would strengthen the experimental evidence. In response, we have expanded our evaluation in several directions, including cross-LLM comparisons on four datasets (W2-ii), shared-hyperparameter evaluation on five datasets (W2-iv), and A-NEC evaluation on BAR and Stanford40 (Response to Reviewer iWmT, W3).
These additional experiments provide broader evidence for the robustness of our design choices across different datasets and evaluation settings. We have incorporated these results into the revised manuscript, with selected findings included in the main text.
Also, we appreciate the reviewer's observation that several relevant experiments are already included in the appendix but insufficiently highlighted in the main text. We have added explicit references to selected supplementary analyses and included key findings in the main experimental discussion.
Q1. Semantic relevance and visual observability
We apologize for the ambiguity in our wording in Section 3.2. Our intention was to distinguish class–concept semantic relevance from image-level concept presence, rather than suggest that ScoreCBM assigns concepts to images solely based on LLM knowledge.
Specifically, LLMScore estimates the semantic relevance of a concept to a class, not whether that concept is present in a particular image. Image-dependent concept supervision is still provided by CLIP image–concept similarities. A high relevance score does not itself cause a concept to be activated in an image. Instead, the relevance scores guide how CLIP supervision is learned: high-relevance associations retain their original supervision, while low-relevance supervision signals are attenuated rather than set to zero, preserving potentially useful visual information. In addition, adaptive ℓ1 regularization discourages the downstream classifier from relying on low-relevance concept–class connections.
In this way, LLM-derived semantic relevance complements rather than replaces CLIP-based visual supervision. While CLIP provides image-dependent information, relevance guidance helps mitigate its potentially problematic associations, including those arising from superficial visual resemblance.
We have revised the wording in Section 3.2, particularly the statement regarding visual observability, to eliminate this ambiguity.
Q2. Handling unclear features in LLM scoring
Thank you for this question. The scoring prompt in Appendix A.3 instructs the LLM to assign a score of 0 when a feature is unclear. Once returned, this score is handled in the same way as other zero relevance scores, without any additional uncertainty-specific processing. Specifically, it is subject to the configured activation attenuation and adaptive ℓ1 penalty, rather than automatically removing the concept or setting its activation to zero. The LLM-generated reasoning is not used during training.
We have clarified this handling procedure in Appendix A.3.
Q3. Cross-LLM agreement and evaluation
Thank you for this suggestion. We have addressed these concerns in our responses to W2-(i) and W2-(ii), where we provide quantitative agreement analysis between Gemini and Qwen and extend their downstream performance comparison to four datasets.
We have also incorporated these analyses into the revised manuscript and highlight the relevant findings in the main experimental discussion, as discussed in W2-(v).
Q4. Direct supervision using binary LLM relevance
We thank the reviewer for this suggestion. We would like to clarify that the LLM-derived relevance scores in ScoreCBM are class–concept semantic priors, rather than image-level concept annotations. They are used to guide concept learning and classifier regularization, while CLIP image–concept similarities provide image-dependent supervision.
Directly using binary LLM relevance scores as concept supervision would assign the same concept targets to all training images of a given class, regardless of whether those concepts are visually present. This would fundamentally change the role of the semantic prior and could introduce the very issue of assigning visually absent concepts that the reviewer raised in Q1.
Our approach instead preserves image-dependent CLIP supervision while using class–concept relevance to suppress potentially problematic associations. We hope this clarifies the distinction between the suggested alternative and the proposed framework.
We thank the reviewer for the detailed and constructive feedback. We have organized our response around two main aspects: clarifying the role of LLM-derived semantic relevance in ScoreCBM and strengthening the evaluation of its reliability and robustness.
First, we clarify an important distinction underlying several questions: LLMScore provides a class–concept semantic prior rather than image-level concept annotations. CLIP image–concept similarities remain the source of image-dependent supervision, while relevance scores guide interventions during concept learning and classification.
Second, we provide additional experimental evidence, including cross-LLM consistency and multi-dataset performance comparisons, shared-hyperparameter evaluation across five datasets, and extended relevance-score corruption experiments. We have also improved methodological clarity and brought selected findings from the appendix into the main experimental discussion.
Detailed explanations and supporting evidence are provided in our responses to the corresponding comments below.
W1. Clarity of the method
We thank the reviewer for the constructive suggestions regarding the clarity of our method. We agree that the preliminaries should be more accessible to readers unfamiliar with LF-CBM.
To address these concerns, we have revised Section 3.1 to first introduce the basic CBM pipeline, which maps images to concept activations and then predicts classes from these activations. We have also clarified the distinct roles of the pretrained visual encoder f and CLIP encoders, the notation for the CLIP activation matrix A and its entries Aij, and how the concept projector learns from CLIP-derived supervision. The revised presentation further clarifies how the two learning stages relate to our relevance-guided interventions.
In addition, we have expanded Appendix A to provide a detailed description of the concept generation and preprocessing pipeline, including the prompts, filtering procedures, and dataset-specific settings. Section 3.1 now provides a concise overview and refers readers to the appendix for reproducibility details.
W2. Consistency and performance across different LLMs
We agree that the reliability of the semantic prior is an important aspect of the proposed framework. We have therefore conducted additional analyses of both the consistency of relevance scores across LLMs and their impact on downstream classification.
(i) Consistency of semantic priors across LLMs.
We thank the reviewer for this suggestion. To examine whether the class–concept relevance prior depends strongly on the choice of LLM, we compare relevance scores generated by Gemini and Qwen for identical class–concept pairs.
For binary agreement, scores of 5–10 are considered relevant and scores of 0–4 irrelevant. The analysis covers all 1,320 pairs on BAR and the same 8,000 CLIP-retrieved pairs on Stanford40, excluding unscored pairs assigned zero by pre-filtering.
Both datasets exhibit high cross-LLM consistency, with Pearson correlations above 0.83 and binary agreement rates above 90%. These results suggest that the semantic relevance judgments used by ScoreCBM are reasonably stable across the two LLMs, rather than being specific to a single model. We have included this analysis in Appendix B.6 of the revised manuscript.
(ii) Performance across different LLMs.
We agree that extending the comparison across more datasets would strengthen the evaluation of ScoreCBM's robustness to the choice of LLM. We therefore report comparisons between Gemini and Qwen on four datasets, including the existing BAR results in Appendix B.2:
The two LLMs achieve broadly comparable performance across these datasets, with accuracy differences ranging from 0.01 to 1.74 percentage points. Together with the cross-LLM agreement analysis in (i), these results suggest that the proposed relevance-guided framework is not highly dependent on a particular LLM, although the choice of LLM can influence performance.
For larger datasets such as Places365 and ImageNet, extensive Gemini-based scoring is constrained by its API quota. Our evaluation on these datasets primarily aims to examine scalability. By using Qwen, a locally deployable LLM, we demonstrate that ScoreCBM can be applied to large-scale classification tasks without relying on a cloud-based LLM. We have incorporated the relevance-scorer comparison into Section 4.4 of the revised manuscript.