- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The author points out that after erasing a concept, CLIP zero sample classification cannot recognize the class, which does not mean that there is no relevant information in it. So, using a small number of labeled samples, the linear classifier was retrained on the erased representation to check if the class could still be recognized. The paper compares methods such as one-way projection and proposes ESP to remove multiple directions at once. The experiment verified the influence of population attributes and group differences.
Critical strengths
- The problem is relatively clear.
- Low evaluation cost and easy reproducibility.
- The main comparison covers a wide range of categories.
- Honest reporting of negative results.
Critical weaknesses
- The abstract is too long, almost occupying the first page. It's hard to understand what the main contribution is. The statement of 0% and group differences in the abstract is inconsistent with the more limited results in the main text. The paper emphasizes the differences in population recovery after erasure, but lacks corresponding experiments before erasure.
- Limited innovation and lack of differentiation comparison with the latest methods.
- Some charts are too large and have formatting issues.
- The current version is not suitable for publication in ICLR.
Questions for authors
- Only reporting the recovery recall rate cannot determine whether the concept can truly be effectively restored.
- The lack of probe controls for non erased representations makes it difficult to quantify how much information has been reduced by erasing.
- ESP has lower advantages compared to simple unidirectional baselines and lacks comparison with the latest methods.
- The fairness section needs to compare the differences before and after erasure. The abstract emphasizes a difference of 8.9 times, but the main text shows multiple sub results ranging from 1.5 to 8.9 times. Can you report the changes in the differences before and after erasure, as well as the absolute difference.
- A large bar chart takes up a lot of space, but lacks error bars;
Guidelines on the Use of AI Tools for Manuscript Review
This review process utilized AI to translate and organize the core content of the manuscript. Subsequently, human reviewers conducted a thorough assessment and finalized the review results. Human oversight ensured the overall quality and formatting of the manuscript, and the final conclusions were determined by human judgment rather than by AI.