- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes VBEDIT, a training-free method to reduce hallucinations in MLLMs. The method first computes the margin between different answer candidates and uses the gradient of this margin to select visual tokens that support or oppose the current answer. Then, it perturbs the most supportive visual tokens by replacing them with the mean visual representation and measures how much the margin changes. Based on this change, the method decides whether the answer needs to be edited or not. If the counterfactual response is larger than a threshold and the predicted answer is "Yes", the method constructs a vector using the positive and negative visual-token centroids and uses it to reduce the margin of the current prediction. The method is evaluated on several MLLMs and benchmarks, including POPE, MME, AMBER-D, and HOPE, and shows improvements over the original models and other hallucination mitigation methods. The paper also provides ablation studies on different components of the method.
Critical strengths
The method addresses an important problem, and it is training-free. The experiments are conducted across multiple benchmarks and models, with adequate ablations on their hyperparameters.
Critical weaknesses
-
The main motivation of the paper is that, in the proposed method, the relevance of the visual evidence is verified, and then the model's answer only changes when it is not visually supported. But I cannot see how the proposed method relates to this motivation. The proposed counterfactual verification measures the sensitivity of the prediction to perturbations of selected visual tokens, not whether it needs to be corrected or whether it is supported by the image.
-
The correction method is not sufficiently justified. It is not clear why reducing the margin should reduce hallucination. There can be multiple cases in which the model is confident about its answer, and the answer is also correct. Also, in the paper, only "Yes" answers are altered, but it is not clear why there should be a difference between the answers.
-
The method is only evaluated on questions with "Yes" and "No" answers, and it is not clear whether it transfers to other types of questions. It is not clear whether reducing the margin works for other types of answers as well, or whether it can be a reliable detection method for hallucinated tokens.
-
A vector is constructed based on the positive and negative centroids, but again, it is aligned with the direction of the margin gradient. So it is not justified why that particular vector is needed. Isn't it possible to use the gradient of the margin directly? The ablation study only excludes the negative centroid, but other update strategies need to be ablated to justify the role of this vector.
Questions for authors
-
The method has multiple hyperparameters, but it is not clear how they were tuned. Please clarify this. If they were tuned on the POPE benchmark, then comparing the results with other baselines taken from their original papers may not be fair.
-
Why should reducing the margin be the strategy for reducing hallucinations? How is it directly connected to hallucination reduction, and why is it limited to "Yes" answers?