- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes a new framework for mitigating cross-modal hallucinations using GRPO. The main contribution of this work is that it creates counterfactual data by corrupting different modalities of an audiovisual stream and enforce that the correct model behavior across those corruptions is rewarded, on yes/no tasks that are based on object/sound presence.
Critical strengths
-
Formulation of TAG-GRPO is easy and it only requires minor tweaks to an existing GRPO pipeline and requires some additional data.
-
The paper has also shows results on general benchmarks beyond cross-modal hallucination benchmarks to show the general performance trend on performing TAG-GRPO.
Critical weaknesses
-
Too similar to GRPO and very less novelty. The paper just creates a new dataset with counterfactual modality corruption and trains GRPO with correctness reward on top of it. The dataset construction pipeline (4.1) and the modality intervention (4.2) is similar to MoD-DPO (CVPR 2026). The paper's claim are somewhat loose (see below) and require more rigorous experimentation to justify that they work.
-
Comparison with GRPO is underspecified. Table 2 and 3 compare TAG-GRPO with standard GRPO but it does not specify the details of the GRPO baseline. Was the GRPO also trained with the same number of data samples, and corruptions as TAG-GRPO? Also, the paper works only with 8 rollouts, but does not specify how the rollouts are divided among the Rob., Sens. and Int. cases. Give only 8 rollouts and GRPO works well with some variance, the results of the paper are underspecified.
-
Bias towards the "No" response. Equation 6 suggests that in the case of Int. and Rob. the response remains the same but in case of Sens. the response changes to "No" irrespective of the question. This can create a bias towards the No response in general. This is also shown in the results, where the precision increases and recall drops for VDAH and ADVH compared to standard GRPO. Additionally, Table 1 shows that there is also some imbalance in the training data as well in terms of Yes/No questions, that can have additional bias effect towards some classes in some category of questions.
-
GRPO Rollout information is missing
- The paper does not mention the split between the (A,V), (A',V), and (A, V') for the A/V tasks. Are the rollouts split between the 8 rollouts?
- In Table-5, for the AV case, the paper shows ablation by changing the number of rollouts split between the different cases. However, having a single sample in a group makes no sense for GRPO as the advantage would come to be zero and that group will have no contribution to the loss.
-
No hyper-parameter sensitivity analysis for (, , ). L352-355 just mention the weights but do not mention the sensitivity of training to these. Moreover, I could not these weights defined in the Method section to specify how they are incorporated to the loss function.
Questions for authors
The authors should address the above concerns mentioned in weaknesses and answer the questions in between. I don't have more questions as there are details regarding GRPO that are not clear as of now. I look forward to the author discussion period to make the assessment of the work better. Good luck to the authors!
6 comments
Response to Reviewer kncQ (2/2)
W3. Bias toward No.
We agree that the Sen target pushes toward No, and we now quantify it App\. F; Yes ratio in %, three-seed means:
| Backbone | Method | ADVH | VDAH | AVM | CMM |
|---|---|---|---|---|---|
| Qwen2.5-Omni-7B | GRPO | 48.27 | 66.81 | 34.89 | 59.38 |
| TAG-GRPO | 45.22 | 64.99 | 35.04 | 57.67 | |
| MiniCPM-o-2.6 | GRPO | 51.47 | 57.98 | 72.92 | 52.69 |
| TAG-GRPO | 44.45 | 47.67 | 45.31 | 47.69 |
All label priors are about 50%. In six of eight backbone–subset pairs, TAG-GRPO moves the Yes ratio closer to 50%, mostly by reducing unsupported Yes answers, e.g., MiniCPM AVM from 72.9% to 45.3%. On VDAH, the precision–recall shift the reviewer notes comes from fewer Yes answers relative to a Yes-heavy baseline. On ADVH, however, the Yes ratio drops to 44–45% on both backbones, which is over-correction, and we state it in the Limitations. On Qwen, AUROC still improves on all three AVHBench subsets, so the AVHBench gains are not only a threshold shift. The strength of the push is controllable through w_Sen App\. E, and the Sen objective has a nominal share of only 6% of the overall objective Sec\. 4\.4.
Regarding the training labels, Yes accounts for 63.7%, 37.9%, and 82.2% of the A, V, and AV tasks and 63.4% overall, so the label imbalance favors Yes rather than No; GRPO is trained on the same labels, so the difference between the two methods comes mainly from the Sen target. We also tested a Cannot determine Sen target; it lowers the AVHBench average by 1.99 and 2.22 App\. E.
W4. Rollout split and singleton groups.
-
For A/V tasks, the 8 rollouts are split as Int/Rob/Sen = 4/2/2 over the intact pair, the pair with the task-irrelevant modality corrupted, and the pair with the task-relevant modality corrupted; for these are , , and .
-
In the AV rollout-allocation table (Table 6, formerly Table 5), both corrupted AV conditions are routed to Sen with target
Noand normalized jointly, so 6/1/1 and 4/2/2 correspond to Int/Rob/Sen = 6/0/2 and 4/0/4. No singleton group arises; we agree that a singleton would receive zero advantage, and we clarified this in the caption and App. B.
W5. Definition and sensitivity of the group weights.
The weights w_{t,g} enter the objective in Eq. 9 Sec\. 4\.4, which divides by their sum so that the per-sample loss scale stays at 1; removing a group sets its weight to 0. The default is 0.7/0.2/0.1 for A/V tasks and 1/0/0 for AV tasks Sec\. 5\.1. App. E reports sweeps of w_Sen ∈ {0, 0.05, 0.1, 0.2} on both backbones and w_Rob ∈ {0.1, 0.3} on Qwen, together with uniform weights and pooled normalization, all with 8 rollouts. AVM and the AVHBench average peak at the default w_Sen = 0.1 on both backbones, raising w_Sen trades PA for HR on Qwen, and uniform weights lower AVM by 3.14–4.69. The full table is in our response to Reviewer b7jN .
We thank the reviewer again for the constructive comments, which have substantially improved the paper. We hope our responses and revisions address the concerns, and we would be glad to discuss any remaining questions.
W1. I still have concerns about the novelty of this work. The main novelty is still only the things that were mentioned in my original response.
W2. For GRPO baseline, I still don't understand that why the authors have kept the groups to be uneven among I/R/S sets. Low group size for R/S sets still provides very noisy signal for training. A more balanced set such as 6/5/5 might give a better reward signal. My understanding is that increasing the robustness or sensitivity group size may reduce the performance of the method.
W4. Routing both the corrupted AV conditions to the sensitivity target does not sound like a good idea. It is not clear why that choice is made. Making that choice removes the effect of the Robustness group from Table 6.
W5. It is unclear what happens at higher or equal weights of the robustness and sensitivity groups and when the weights of all the groups are set equal to each other.
My current rating reflects my evaluation. I thank the authors for their hard work preparing the responses!
Response to Reviewer kncQ (1/2)
We thank the reviewer for the comments.
W1. Novelty relative to GRPO and MoD-DPO.
We acknowledge that our diffusion-based corruption follows VCD Sec\. 3 and takes the strength s = 500 from MoD-DPO Sec\. 4\.2; our dataset is a binary QA set built from VGGSound. The contribution lies in the training objective: task-dependent conditions are routed into groups with evidence-conditioned targets and optimized on-policy. The GRPO baseline uses exactly the same data, so the comparison isolates the objective rather than the dataset, and new controls isolate each ingredient with the same data and rollout budget Sec\. 5\.3, Table 5, App\. D:
Same data, ordinary GRPO: over three seeds, TAG-GRPO improves the AVHBench average by 0.59 p=0˙02 on Qwen and 4.09 p=0˙33 on MiniCPM, and CMM HR by 2.41 and 7.56.
Same corrupted inputs, no target flipping All−Rob: not consistently helpful; relative to GRPO, AVM changes by −4.59 and +5.70, the latter with HR −5.69.
Same conditions and targets, offline TAG−DPO: the AVHBench average drops relative to DPO by 0.58 and 1.45.
MoD-DPO trained on the same data: TAG-GRPO is higher on the AVHBench average by 4.29 and 1.46 and on CMM balanced accuracy by 1.29 and 4.17 (single runs, Tables 2–3).
We have also tightened our claims: the logit-based analysis App\. F shows where TAG-GRPO improves discrimination and where it mainly shifts the operating point, as detailed in W3 below and in the General Response.
W2. GRPO baseline and rollout split.
GRPO uses the same 7,944 training samples, the same regular-expression-based binary reward, the same hyperparameters (LoRA configuration, learning rate, number of epochs), and 8 rollouts per sample, all on the intact input with the teacher answer; it uses no corruption. TAG-GRPO uses the same budget: for A/V tasks, Int/Rob/Sen = 4/2/2, and for AV tasks, 8 intact rollouts Sec\. 5\.1, App\. B. To address variance, we report three seeds per method with Welch's t-tests App\. C; General Response 1/2. We also doubled the budget to 16 rollouts per sample: TAG-GRPO with 12/2/2 remains above GRPO on all three AVHBench subsets, by 0.44, 1.14, and 1.49, and is nearly tied in CMM balanced accuracy, +0.08 single runs, App\. C.