- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates Grounded Control Reversal (GCR): a correct, visually supported answer preference emerges in intermediate layers of a multimodal model but is subsequently overturned before the final prediction. The authors study this phenomenon through layerwise prediction tracing, same-image visual-pathway interventions, and Shapley attribution across visual attention, textual attention, and feed-forward updates. Building on this diagnosis, the paper proposes ReCAP, a training-free decoding method that selects a persistent, visually supported intermediate candidate and applies a minimum-norm projection to the final hidden state to restore its advantage over the original prediction. Evaluation covers two 7B backbones and multiple hallucination and general-capability benchmarks. Additional experiments examine anchor reliability, alternative correction rules, preservation of useful content, and inference overhead.
Critical strengths
The mechanism analysis includes meaningful intervention controls. The paper does not infer visual grounding solely from a correct intermediate prediction. It includes visual-value suppression, sham replay, norm-matched random perturbations, and norm-matched nonvisual perturbations. Importantly, Table A2 evaluates these controls before applying the positive visual-support filter, reducing the risk that the filtering criterion itself produces an apparently positive effect. Table A4 additionally examines correspondence between the online support score and the intervention-based measure. These experiments make the diagnosis more persuasive than layerwise correlations or attention visualizations alone.
The correction is precisely formulated and supported by useful empirical analyses. ReCAP has a closed-form correction, and the matched-anchor comparisons in Table 5 and Appendix E help separate the effects of anchor selection from correction geometry. The reported improvements are practically relevant: Qwen’s POPE accuracy increases from 84.82% to 89.38%. Table A5 further shows that ReCAP corrects 562 original errors while introducing 152 new errors, making the net benefit explicit. Content-retention and general-capability evaluations provide additional support for the method’s practical
Critical weaknesses
The contribution of reversal-aware triggering is not clearly isolated. Section 4.1 defines and requires an eligible anchor to satisfy . Except when final logits are tied, an eligible anchor therefore already satisfies , making the subsequent reversal check redundant. However, Section 5.4 describes an always-on variant that additionally intervenes when a supported preference weakens without reversing. It is unclear how such cases arise under the stated definitions. If the variant also changes the candidate selection, competitor, or correction rule, its performance difference cannot be attributed solely to the reversal trigger. A precise description of this variant and the conditions under which it differs from ReCAP would help resolve this concern.
The mechanistic novelty relative to DeCo needs sharper positioning. DeCo[1] already reports that correct visual predictions can emerge in intermediate layers and subsequently be suppressed or overtaken by hallucinated predictions in later layers. Its decoding method also uses candidate filtering, dynamic intermediate-layer selection, and final-output correction. Thus, the broad phenomenon underlying GCR substantially overlaps with an existing observation. The present paper adds meaningful elements, including persistence requirements, same-image visual-pathway interventions, route attribution, and pairwise residual projection. However, these additions support a more precise diagnosis and a different correction strategy more directly than the discovery of an entirely new failure mechanism. The authors should clarify which mechanistic conclusions go beyond DeCo and connect those claims to the intervention evidence already provided. This distinction is consequential because mechanism discovery is presented as a central contribution.
[1]Wang, Chenxi, et al. "Mllm can see? dynamic correction decoding for hallucination mitigation." International Conference on Learning Representations. Vol. 2025. 2025.
Questions for authors
- Clarification of the always-on ablation. Since and an eligible anchor must satisfy , the reversal condition appears to follow automatically when the final maximum is unique. How does the always-on variant encounter cases where a supported preference weakens without reversing? Please clarify whether this variant changes anything besides the trigger, such as candidate selection, the competitor, or the correction rule.
- Clarification of targeted validation. Please clarify whether the baselines received comparable tuning opportunities. Paired confidence intervals for the main comparisons would help assess the smaller improvements. If the reported test sets informed parameter selection, a limited evaluation on held-out data with fixed parameters would help resolve this concern.
- Clarification of the mechanistic contribution relative to DeCo. DeCo already describes correct visual predictions emerging in intermediate layers and subsequently being suppressed or overtaken in later layers. Which specific mechanistic conclusions of GCR go beyond this observation? Please identify how the existing persistence analysis and visual-pathway interventions establish the additional contribution, and clarify whether GCR is intended as a distinct failure mechanism or a more precise operational characterization of the previously observed phenomenon.