- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes FB-LoRA, a method for Bayesian sampling of LoRA factors.
Critical strengths
- The structure is simple. Using “dependent factors” to set div M = 0 is a clean design. It avoids costly drift corrections, and the computation involves only r×r matrices, resulting in minimal overhead
Critical weaknesses
- The Identity method achieved an ECE of 21.65 in Table 1 and an AURC×100 of 21.65 in Table 2; these are two different metrics but the same value. 2The ASR values for all baselines fall within the range of 74–78% but the method described in this paper achieved 14% only; Can authors provide the raw logs or code for reproducibility?
- There is a 62% difference in ASR between Dynamic Diagonal Gram and Dynamic Gram. What is the source of this discrepancy?
- Baseline is not fair enought
- The safety result contradicts Theorem 2
- please carefully check all numbers described in the paper;
Questions for authors
see above