- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper asks why medical LVLMs answer yes/no concept-presence questions wrongly when linear probes can still read the concept from hidden states. Tracing the encoder, connector and decoder of three models, the authors argue the decoder fails to use this information. They propose MedSteer, a probe-gated activation edit that raises accuracy by 5 to 13 points over unedited models and beats steering and decoding baselines.
Critical strengths
-
The analysis traces concepts from the vision encoder to the decoder and corroborates correlational findings with activation patching, across three models and multiple modalities. The appendix is candid about the limitations of each test.
-
MedSteer is lightweight: 64 positive examples per concept, two forward passes, no fine-tuning. It improves all model and modality combinations in Table 2, which matters in practice if the gains withstand the controls below.
Critical weaknesses
-
The paper interprets high probe accuracy as evidence that the concept remains decodable in the decoder. However, since the probe is trained with explicit labels, high accuracy only demonstrates that a linear classifier can separate the two classes, not that the model itself retains or utilizes the concept.
-
Table 3 is difficult to interpret. The paper does not specify which SLAKE questions are used (closed-set, open-set, or the authors’ own presence template), nor how the 155 CT and 60 MRI samples were selected. These sample sizes are also limited.
-
All main results are derived from yes/no presence questions constructed from segmentation labels. The paper does not verify whether MedSteer can improve model performance on real downstream tasks such as the full SLAKE test set or full IU-Xray report generation.
Questions for authors
-
The decoder probe accuracy reflects how well the probe can predict, from the decoder representation, whether a given layer still retains the concept. Why does high probe accuracy indicate that the concept is decodable?
-
SLAKE contains both closed-set and open-set questions. Which subset is used in Table 3, how were the 155 CT and 60 MRI samples selected, and are they exclusively yes/no presence questions?
-
MedSteer improves concept recognition on presence questions. Does this generalize to real downstream tasks? Results on the full SLAKE test set and full IU-Xray report generation task would substantially strengthen the case.
4 comments
>>> Response to W3 and Q3: Following the reviewer’s suggestion, we evaluated MedSteer on the full SLAKE English test set and the full IU-Xray report-generation test split. Because MedSteer operates on concepts with learned steering directions, we use the following protocols.
SLAKE. We apply the gated edit when a question mentions a concept in our modality-level concept pool and leave other questions unedited. Of the 1,061 test questions, 470 receive an edit, and 591 remain unedited. The reported metrics cover the full test set, including both groups. For closed-ended questions, we report accuracy. For open-ended questions, we report recall, defined as the fraction of ground-truth answer tokens that appear in the generated answer, averaged over questions.
Table R7. Full SLAKE English test set (n = 1,061; 470 questions edited). Scores are percentages, reported as unedited → MedSteer. We report accuracy for closed-ended questions and recall for open-ended questions.
| Model | Closed-ended accuracy | Open-ended recall |
|---|---|---|
| MedSIGHT | 70.9 → 74.6 | 55.3 → 57.2 |
| Lingshu | 84.6 → 86.3 | 75.2 → 76.1 |
MedSteer improves closed-ended accuracy by 3.7 and 1.7 percentage points and open-ended recall by 1.9 and 0.9 percentage points for MedSIGHT and Lingshu, respectively. These are full-test-set improvements under a protocol that targets the 470 concept-matched questions.
IU-Xray. We apply gated MedSteer edits for seven candidate chest X-ray finding concepts, including lung lesion and pleural effusion, to every test image. Each concept’s probe determines its edit sign for that image. We use the same generation setting as in Table 4 (Table 5 in the revised version) and evaluate the complete generated reports.
To assess report quality beyond target-concept accuracy, we report F1 over all 14 CheXpert findings for finding-level agreement, which is computed as micro-averaged F1 over positive labels. We also report ROUGE-L for lexical overlap, and RadGraph F1 for clinical entity and relation agreement.
Table R8. Full IU-Xray test split (n = 590 studies, one reference report per study), using the generation setting from Table 4 (Table 5 in the revised version). Scores are on a 0–100 scale, reported as unedited → MedSteer.
| Model | F1 over 14 findings | ROUGE-L | RadGraph F1 |
|---|---|---|---|
| MedSIGHT | 14.7 → 15.8 | 13.7 → 15.2 | 16.6 → 20.2 |
| Lingshu | 27.5 → 28.6 | 28.8 → 30.0 | 32.0 → 32.5 |
MedSteer improves all three report-generation metrics for both models. Together with the full SLAKE results, these findings provide evidence that its benefits extend beyond templated presence questions to the evaluated downstream VQA and report-generation tasks. The gains vary across models and metrics, and the intervention remains limited to a predefined concept pool. We have added both evaluations and clarified their scope in the revised paper.
Revision: Both evaluations are summarized in Section 7.5 (page 10, lines 515 and 529–531), with full results in Appendices E.2 and E.4.
We thank the reviewer again for the suggestions, which have helped us clarify the interpretation of our analyses and strengthen the downstream evaluation. We have incorporated these changes into the revised paper.
I thank the authors for their efforts. The additional clarifications and explanations have adequately addressed my concerns. I therefore recommend accepting the manuscript and will maintain my original positive score.
We are glad that our additional clarifications have adequately addressed the reviewer's concerns. We sincerely appreciate the reviewer's time, thoughtful consideration, and continued support of our work.
We thank the reviewer for the constructive feedback and for highlighting the need to clarify our probe interpretation, evaluation protocol, and downstream applicability. We address each concern below.
>>> Response to W1 and Q1: We agree that high probe accuracy alone does not establish that the model uses a concept when generating an answer. In our paper, “decodable” means that information about the concept label is linearly recoverable from a frozen representation. As stated in Section 4, “Linear probes test whether a target property can be recovered by a simple classifier from frozen representations” (lines 132–133; Alain & Bengio, 2017; Belinkov, 2022).
The explicit labels supervise the linear readout, and they do not modify the frozen LVLM. High probe accuracy on held-out, patient-disjoint test data therefore indicates that the representation contains features predictive of concept presence that are accessible to a linear classifier. This is the operational meaning of “decodable” in our analysis. It does not, by itself, establish that these features constitute a faithful semantic representation of the concept or exclude reliance on correlated features.
We also explicitly distinguish recoverability from use: “probe performance measures whether concept information is recoverable from a representation by a linear readout. It does not establish that the model itself uses this information when generating an answer” (§4, lines 157–159). This distinction is the central premise of the paper and motivates the complementary analyses in Sections 6–7. Attention and activation analyses characterize associations with model behavior, while activation patching and steering test how interventions affect the model’s answers.
To avoid ambiguity, we will define “linearly decodable” explicitly at its first occurrence and replace ambiguous statements that a layer “retains the concept” with the more precise wording “contains linearly recoverable information about the concept label.”
Revision: The definition is now stated explicitly in Section 4 (page 3, lines 159–161), and the wording is revised in Section 1 (pages 1–2, lines 52–59).
>>> Response to W2 and Q2: Thank you for identifying this omission. Table 3 (Table 4 in the revised version) evaluates whether the kidney and liver directions learned from CT data transfer to new data. We therefore select SLAKE’s original English closed-ended questions asking whether a kidney or liver is present.
We include all eligible questions from the SLAKE English test set whose associated image is CT or MRI, with no additional filtering. This yields 155 CT and 60 MRI question–image pairs. All selected questions are yes/no presence questions from SLAKE itself, and they are not generated using our segmentation-derived templates.
We agree that this is a limited, targeted transfer evaluation. The sample sizes reflect the number of eligible questions in the test set. We have specified the question source, inclusion criteria, and unit of counting in the description of Table 3 (Table 4 in the revised version). To complement this evaluation, we also report results on the full SLAKE English test set in Table R7 below.
Revision: These details are now given in Section 7.5 (page 10, lines 509–512) and Appendix E.1 (page 32).
References