- Rating
- 4(+1)
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces a large-scale multimodal AIGC detection dataset with multi-granularity CoT annotations and a unified detector for image, video, and text, motivated by the limitations of existing datasets and the lack of unified detection methods. To address the optimization dilemma between reasoning and detection, the paper proposes a three-stage training paradigm to improve artifact perception, evidence-grounded reasoning, and evidence-verdict consistency. Extensive experiments across various evaluation settings and benchmark datasets demonstrate strong detection performance and robust generalization.
Critical strengths
-
The introduction of a large-scale multimodal AIGC detection dataset with multi-granularity CoT annotations provides an important resource. It addresses the limitations of existing datasets in terms of data scale, modality coverage, and annotation granularity.
-
The paper is well motivated, and the proposed method is reasonably designed. The proposed three-stage training paradigm addresses the lengthy CoT optimization dilemma and shows generalizability across architectures. Extensive experiments and ablations support its effectiveness.
Critical weaknesses
Although Figure 2 compares different SFT strategies, the effect of response length on detection accuracy remains unclear. I suggest an additional analysis of different SFT response lengths to better support the paper's motivation.
Questions for authors
-
The calculation of the OOD metric should be further clarified, particularly the inclusion of the "Real" column in the main tables but not in the ablation experiments.
-
Figure 4 incorrectly uses "APP Loss" instead of "AAP Loss".
-
The caption of Table 6 mentions three cross-dataset benchmarks, whereas four are reported.
-
The quality threshold τ in Figure 3 is not explicitly specified, and the aggregation of evaluation scores could be clarified. The verification prompt and the content extracted by Reason(⋅) in Eq. (9) are not sufficiently specified.
4 comments
Response to the rebuttal
The authors have addressed my questions. Given the contributions of the dataset and training paradigm to the field of AIGC detection, I will keep my recommendation to accept the paper.
We thank the reviewer for their positive feedback. We will incorporate these revisions into the final version.
Thank you for recommending acceptance. We would appreciate it if you could update your rating.
We thank the reviewer for their valuable feedback.
We further investigate the effect of SFT response length by comparing the full response with four shortened variants. As shown in table A, the full response achieves the highest OOD accuracy across all three modalities. Shortening the reasoning components substantially degrades image and video accuracy by 6.56–8.35 and 21.77–23.97 percentage points, respectively. These results indicate that simply shortening CoT is not an effective way to alleviate the reasoning–detection optimization dilemma.
Table A: OOD accuracy (%) and average SFT response length (tokens, in parentheses).
For each modality, each unseen generator is evaluated on 400 fake samples together with the same shared set of 400 real samples. Thus, each generator column in the main tables reports accuracy over these 800 samples, while the “Real” column separately reports accuracy on the 400 real samples.
In the ablation tables, OOD accuracy is the macro-average across unseen generators, with equal weight for each generator. The “Real” column is excluded from this average because real-sample performance is already included in each generator's accuracy.
We thank the reviewer for pointing out these errors. We make the following corrections:
(1) Figure 4: Corrected the label from "APP Loss" to "AAP Loss".
(2) Table 6: Corrected the caption from "three cross-dataset benchmarks" to "four cross-dataset benchmarks" to match the four benchmarks reported in the table.
We clarify the following details:
(1) Quality thresholds and score aggregation. Each judge scores six dimensions (1–5), with scores averaged across dimensions and judges. The review and acceptance thresholds are 3.0 and 4.5, respectively. Samples below the review threshold undergo human revision. Additionally, acceptance requires every judge to score at least 4.5 on each dimension. Otherwise, iterative refinement continues for up to three rounds.
(2) Verification prompt and reasoning extraction. We clarify that Reason(⋅) extracts and concatenates the
<thinking>,<key_features>, and<explanation>fields, excluding<answer>. We add the verification prompt for Qwen3-4B-Instruct-2507 in Appendix fig. 24.