- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper asks whether fixation heads in medical vision-language models are reliable explanations of image use, or controllable components of generation. It follows their inheritance through medical tuning, evaluates several attention-based read-outs, and then intervenes on the same heads. The proposed ACG generates responses under explicit regional steering, and MedGaze learns anatomical attention through a decoding-only adapter on selected query rows. Experiments span 25 models and six corpora, with different subsets for individual evaluations. Results show that native attention is unreliable under the tested read-out protocols, steering changes regional descriptions and improves finding F1 in a controlled report-tour setting, and MedGaze improves organ-question accuracy and anatomical attention without test-time masks.
Critical strengths
-
Steerability and readability are separated in the same components. Sections 5.2–5.3 intervene on and explain the same fixation heads. Steering changes generated descriptions, while native attention localizes poorly and detects its own errors poorly, and the temporal analysis shows attention shifting substantially between reasoning and answering.
-
The controls are more than decorative. Paired base-to-tune comparisons, held-out montage transfer and the random-head controls each close off a different alternative explanation, and the answer-only adapter separates anatomical alignment from ordinary supervised task learning. The identical-prompt report tours are the cleanest of these, since they rule out the reading that the model was simply asked about anatomy.
-
The inheritance analysis provides insight into what medical adaptation preserves. Section 5.1 and Figure 8 examine corresponding heads in base models and medical tunes, rather than comparing only downstream accuracy. All four supervised Qwen tunes retain their base’s top fixation head, and fixation matrices remain strongly correlated across the paired checkpoints. This provides a concrete account of how spatial-routing behavior survives adaptation and offers a useful starting point for studying how different tuning procedures modify model internals.
-
Table 6 evaluates several attention- and gradient-based methods against random boxes matched to each method’s proposal sizes. This matters because large proposals can obtain favorable overlap without identifying informative evidence. Comparing each method with its own geometric baseline makes the localization audit more convincing than comparing heatmaps visually or using a single unmatched random baseline. The result is a useful evaluation procedure beyond the fixation-head method itself.
Critical weaknesses
-
Table 9 shows that organ attention rises from 0.092 to 0.333 while visual reliance moves from 0.35 to 0.23, and the change is not significant after correction. The counterfactual variant is more convincing about regional dependence, but it optimizes a different objective, so it cannot be used to rescue the default model's interpretation. I am not convinced the default MedGaze learns content-dependent provenance. The same gap opens on the ACG side, where the masking experiments establish dependence on a steered region more directly than they support individual clinical claims. Learned attention alignment and evidence-faithful generation are different contributions, and the paper currently claims both.
-
The localization evaluation lets candidate regions do part of the work. Table 7 reports SLAKE organ masks at a hit rate of 0.919 against a stated chance of 0.880, and those masks share their source with the evaluation boxes. A 0.039 margin is narrow enough that the definition of the chance level carries the result, and I could not find that definition in the table or its caption. The report-tour evaluation also uses dataset-provided anatomical boxes. Without a source-matched selection baseline, and without separating annotation-assisted from automatic-region results, a high localization score remains ambiguous between good selection and good candidates.
-
The aggregate VQA improvement masks substantial differences between question types. Table 10 reports a much larger accuracy gain on yes/no questions than on organ-choice questions, while Appendix D.5 states that approximately 85% of the yes/no answers are positive. The improved MCC indicates that the gain is not simply a constant-answer effect, but response calibration and learned answer priors remain plausible contributors.
Questions for authors
-
What supports the provenance reading of default MedGaze? Beyond anatomical attention alignment, what evidence shows the default model learns content-dependent provenance?
-
How does steering-based selection compare against a source-matched baseline? Run random selection and a simple prior over the same candidate masks ACG uses, then report IoU and results stratified by candidate count, especially for images with multiple eligible regions.
-
Which reported gains survive an automatic segmenter?
3 comments
Official Comment by Reviewer fXVr
I've read the response and revision. My first weakness is addressed by assigning provenance to ACG and alignment to MedGaze. The other two are also addressed in substance, so I will not repeat them.
- The abstract states that MedGaze matches the answer-only adapter in accuracy while outperforming training-free decoders. Table 1 suggests that the accuracy gains are largely shared with the answer-only adapter. The paper should make clearer what MedGaze adds beyond answer-only adaptation, especially when presenting accuracy gains.
- Section 3.4 defines provenance in terms of dependence on a region and separates it from clinical correctness. This distinction should be maintained throughout the paper, including when describing a region as supporting a sentence. The 74.9% result in Appendix G.5 measures relative dependence for reference phrases under steering; it does not establish that the region clinically supports each generated sentence.
- G.9 finds that masking the cells with the highest fixation-head attention affects phrase probability no more than masking an equal-area random region. Section 5.5 finds that training the heads’ query rows with an attention term reduces reliance on a learned shortcut. These results concern different settings, but their relationship deserves discussion. One possibility is that steering or training creates a dependence that was not present in the unmodified model, rather than revealing an existing one. The paper should clarify whether this is the intended interpretation.
The work remains substantial in scale and includes meaningful controls. The shortcut experiment, in particular, provides a strong basis for the paper’s central story. The paper would benefit from a clearer account of how the control channel, provenance, and accuracy results contribute to that story, and which benefits are specific to MedGaze.
Follow-up Response (1/1): What MedGaze adds, dependence vs correctness, and how the results fit together
Thank you for reading the response and the revision, and for the updated assessment. We are glad that the three weaknesses are addressed and that the shortcut experiment gives the central story a strong basis. Your three suggestions are now in the revised PDF, highlighted in green.
1. What MedGaze adds beyond answer-only adaptation. The accuracy gain over the frozen model is shared with the answer-only adapter, and §5.5 now says so where the gain is presented. At that accuracy, four benefits are specific to MedGaze:
- Attention. The heads move onto the organ: 0.33 against 0.09 for the answer-only adapter, in 14 of 14 models.
- Robustness. The learned shortcut shrinks from 30.7 to 12.7 points, with higher accuracy on uncued images (84.5% vs 78.5%), while a control without the attention term keeps the shortcut.
- Visual reliance. It stays higher under adaptation: 0.23 vs 0.18 nats, 12 of 14 models (Holm ).
- Reports. They gain findings: 27.2 vs 25.4 finding F1, 9 of 10 models ().
In the revision: Section 5.5 (new sentence) and Appendix G.10.
2. Dependence and clinical correctness. We agree, and this is the paper's definition: a region is the provenance of a sentence when the sentence depends on it, and clinical correctness is a separate check by a radiologist or a labeller (§3.4). Appendix G.5 now states this for the 74.9% result: it scores dependence under steering on reference phrases, and the clinical correctness of generated sentences is measured separately, by the finding F1 of the reports (§5.6).
In the revision: Appendix G.5 (added a new sentence) and Appendix G.10.
3. How G.9 and the shortcut result relate. Yes, that is the intended interpretation, and it is the paper's central claim: the write creates a dependence that the unmodified model does not have, rather than revealing an existing one. Three results show it.
- Unmodified model. The cells the heads attend are used no more than a random region (G.9), and blanking a tour box moves report F1 only from 21.9 to 17.3.
- Region written by steering. With the same box written into the heads, blanking it lowers F1 from 30.6 to 16.7, which is 9.2 points more than without steering (, 8 of 9 models).
- Region learned by training. The attention term acts on the same channel. It lowers the heads' attention on the predictive cue from 0.068 to 0.016 and the shortcut gap from 30.7 to 12.7 points, while the control without it keeps both.
G.9 and the shortcut result are therefore two sides of one finding. The heads' attention does not report what the model uses, and setting it, by steering or by training, changes what the model uses. This is the sense of the title: the heads are steerable but not readable.
In the revision: Appendix G.10, which gives this account in one place: how the control, provenance and accuracy results fit together, and which benefits are specific to MedGaze.
Thank you again for your close reading and your thoughtful engagement throughout the discussion. Your suggestions have made the paper's account of its own results clearer and its claims more precise, and we sincerely appreciate the time and care you have given to this work. We hope that these responses and the revision address your suggestions to your full satisfaction.
Regards.
Response (1/1): Provenance via ACG, source-matched selection and the yes/no prior
We thank the reviewer for the careful reading and for the positive assessment of our method and findings. Here are the responses to the minor concerns:
W1 / Q1. Provenance and default MedGaze. We agree that learned alignment and evidence-faithful generation are different contributions, and the revision assigns them explicitly (Sec 3.4, Sec 5.4, and Sec 5.5).
W2 / Q2. Selection vs candidates. Chance is the mean over images of one over the number of candidate regions, which is the expected hit rate of random selection; the revised Table 7 caption defines it. About 70% of SLAKE images have a single eligible organ, which compresses the overall margin; on images with several candidates the fixation heads reach 61.7 against 39.4 chance. SLAKE's masks are the corpus annotation (the source of the evaluation boxes) and the chest masks are automatic; Table 7 now marks which is which. Candidates are whole organ masks, so a hit is the case IoU = 1 with the target. The source-matched comparison: same candidates and selection rule, written into the fixation heads or into 100 random heads (mean of 3 draws), 8 models, hit rate in %:
The write is head-specific: the fixation heads beat random heads at every candidate count and random selection everywhere, and on automatic chest candidates they also beat the size prior (17.2 vs 10.3). The size prior is blind to the sentence. It scores high on SLAKE only because the asked organ is the largest candidate in 74.6% of multi-candidate images, and it would give every sentence the same organ, whereas the write follows each sentence to its own region. In ACG that region comes from the tour or the user, one per sentence.
Q3. Gains with an automatic segmenter. Every headline gain except the SLAKE blanking tests has an automatic-region or region-free version. SLAKE ACG with automatic SAM masks reaches 2.3× chance (0.210), and chest ACG uses an automatic segmenter, reaching 1.8× chance on MS-CXR and 2.0× on VinDr-CXR (25 models). With segmenter masks instead of Chest ImaGenome boxes, the steered report tour adds +6.4 F1 over its heads-off tour (Holm p=0.035), on par with the box tour (Holm p=0.16 for the difference). MedGaze takes no region at test.
W3. Yes/no gains and the answer prior. On a label-balanced set (424 held-out presence questions, half "yes", 14 models):
Both adapters move the "yes" rate toward the training distribution, and discrimination improves beyond that prior: MedGaze's AUROC, which does not depend on the decision threshold, rises over frozen in 13 of 14 models (p=0.0004), and its MCC in 12 of 14 (p=0.002; Holm 0.012). The prior is shared by both adapters, so it does not enter the comparisons that isolate the attention term.
Changes in the revision. §Sec 3.4, Sec 5.4 and Sec 5.5 assign provenance to ACG and alignment to MedGaze; Table 7 defines chance and marks region sources; the appendix adds the source-matched selection table and the balanced yes/no table; new Figure 7 shows the shortcut result. The method, the main results and the conclusions remain unchanged. All changes are highlighted in yellow.
We are grateful for the constructive feedbacks. We hope these results and discussions address your concerns, and we would be glad to answer any further questions.