- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents Feature Enhance, a training-free method for mitigating temporal hallucinations in Video-LLMs. It emphasizes foreground visual tokens and adds inter-frame feature differences before the frozen language model. Experiments on VideoHallucer and EventHallusion across three backbones show consistent gains over the base models.
Critical strengths
- The method is training-free and simple.
- All methods are fairly compared with the same fixed frames and decoding settings.
Critical weaknesses
My concerns are mainly in the experiments.
- In Table 2, the gains mainly come from non-temporal categories (e.g., SDH up to +8.50), while TPH gains only 1.71–3.87. This does not align what this works aim to address.
- The reimplemented SEASON [2] is much weaker than reported in its original paper, in both accuracy (Table 2 vs. Table 1 of [2]) and latency.
- Figure 1 implies that SEASON fails on temporal hallucination, but SEASON outperforms Feature Enhance on EventHallusion MIX for all backbones (Table 2). Also, most of the VidHalluc TSH gain comes from adding temporal-negative contrastive decoding, not from Feature Enhance itself (Table 14).
- No general video benchmark (e.g., Video-MME [1]) is evaluated.
Questions for authors
Please refer to the weakness part.