- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper observes that learned, input-dependent steering vectors (L2S) carry useful sample-specific information but generalize poorly in direction (Fig. 2).
Method.
- S2S decomposes the MLP-predicted vector as , the CAA mean plus a residual (Eq. 3).
- It SLERP-interpolates the normalized residual toward the mean direction (Eq. 5).
- The calibrated direction is used additively (S2S-L) or as a rotation target (S2S-R).
- S2S-R adds a "similarity-aware adaptive weighting" (AW) over the hidden-state, mean, and residual directions, together with a margin gate (Eqs. 9–12).
- Two theorems motivate the design: a reachability superset (Thm. 1) and residual shrinkage reducing MSE (Thm. 2).
Validation.
- On TruthfulQA with Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct, S2S-R reports MC averages of 60.01 / 64.41, versus 53.16 / 51.56 for the strongest baseline, Spherical Steering (Table 1).
- Zero-shot transfer to five other MC benchmarks is reported for Llama (Table 2).
Critical strengths
- A clear diagnosis of why learned steering vectors underperform. Fig. 2 separates direction error from magnitude error, and shows that oracle sample-specific vectors help much more than the mean while predicted ones do not. This is a useful framing for the learned-steering literature, and the plug-in calibration applies to several learned interventions (L2S, LoFiT, LoReFT; Fig. 4c).
Critical weaknesses
-
The main results are internally inconsistent. Table 3 (the ablation) is stated to be on Llama-3.1-8B-Instruct (App. B.7) and reports MC1 = 67.40 for full S2S-R. Table 1 reports MC1 = 57.17 for the same method and model. The "no component" row of Table 3 (41.42) also matches neither the Llama baseline in Table 1 (34.15) nor any baseline method. It is unclear which numbers are representative.
-
The ablation does not support the central claim. In Table 3, the S2S calibration itself moves MC1 only from 41.42 to 43.14. Adaptive weighting then jumps to 66.91. No experiment applies the weighting and gate without the calibrated residual, so the paper's thesis, that calibrating learned directions is what helps, is not supported. In addition, under MC scoring each candidate answer receives its own similarity-gated intervention. This may act as an answer classifier rather than steering, which is consistent with S2S-R not leading on open-ended TRUE×INFO.
Questions for authors
Questions For Authors
All questions are clarifications that could change my assessment.
- Please reconcile Table 1 and Table 3 for Llama (MC1 57.17 vs. 67.40; baseline 34.15 vs. 41.42). Which configuration produced each?
- What does adaptive weighting + gate achieve with the mean direction only (no residual)?
- During MC scoring, is the intervention computed separately for each candidate answer, and does the gate fire at different rates for correct and incorrect candidates?
Response to Reviewer 4TRD [Part 4/4]
Thank you for pointing out these omissions. We will add citations and discussion of the following studies in the revised manuscript and clarify their connections to and differences from our work.
Thank you for this important question about the mechanism. The mean direction serves as a relatively stable reference. Its alignment with the reference direction for individual samples should be distinguished from the overall effect of the calibrated intervention.
(1) Trade-off between directional quality and stability: The learned sample-specific direction can offer better alignment with the oracle direction, but is susceptible to prediction errors on test data. The mean direction may have lower oracle cosine similarity, yet provides a more stable shared reference across training and test data. Calibrating toward this reference balances sample-specific directional quality with stability, potentially reducing prediction noise and improving downstream performance.
(2) Theoretical support: Consider the decomposition
vi∗=vˉ+ri∗,ri=ri∗+ϵi,
and the shrinkage estimator
viβ=vˉ+βri.
Assuming that the expected cross term between the residual signal and noise is zero and that their second moments are finite, we obtain
=(1-\beta)^2S+\beta^2N, \qquad \beta^{\ast}=\frac{S}{S+N},$$ where $S=\mathbb E\|r^*_i\|^2$, $N=\mathbb E\|\epsilon_i\|^2$, and $S+N>0$. Under these assumptions, appropriately shrinking a noisy residual can reduce its mean squared error. This provides an explanation for the benefit of a stable shared reference. > **Q2: Does Table 2 evaluate cross-task effects of steering learned on TruthfulQA?** **In Table 2, the MLP is trained independently on each benchmark and evaluated on its corresponding test set:** COPA, StoryCloze, MMLU, WinoGrande, and BoolQ. The purpose of Table 2 is therefore to evaluate the applicability of the S2S framework across multiple reasoning tasks. It does not directly transfer steering vectors learned on TruthfulQA to these benchmarks and cannot establish whether TruthfulQA-based steering has adverse effects on other tasks. We will replace “cross-benchmark generalization” in Section 6.1 with “evaluation across multiple benchmarks” and clarify the independent training setup. > **Q4: Has BiPO already learned better directions?** Thank you for suggesting this valuable comparison. We agree that a stronger vector-learning method may provide a better reference direction. To examine its complementarity with sample-adaptive calibration, we replace the training-set mean anchor with a BiPO vector and combine it with the MLP. The configurations are as follows: MLP + CAA ($h'=h+\hat v$, $\alpha=1$); Mean anchor + MLP + S2S-L (strength = 1, $t=0.2$); BiPO (strength = 1); and BiPO + MLP + S2S-L (strength = 1, $t=0.2$). | Method | MC1 | MC2 | MC3 | | --- | ---: | ---: | ---: | | MLP + CAA | 37.58% | 57.09% | 29.69% | | Mean vector + MLP + S2S-L | 44.92% | 65.33% | 36.20% | | BiPO | 60.18% | 78.21% | 55.77% | | BiPO + MLP + S2S-L | 63.77% | 82.47% | 57.93% | These results suggest that a stronger shared anchor and sample-specific calibration can be complementary. --- Thank you again. We will incorporate these clarifications and results to better explain our method's mechanism, applicability, and limitations. Best regards, The Authors