- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes Projection-Transport Steering (PTS), a training-free activation steering method that separates the decision of when to intervene from the action of how to modify model activations. It uses a likelihood-ratio test to identify inputs requiring intervention and an optimal transport map to modify activations within a low-dimensional behavioral subspace. The paper also provides a theoretical framework for analyzing steering selectivity. Results suggest that PTS can improve selective behavioral control while preserving task accuracy or retaining more desirable outputs than several baseline methods.
Critical strengths
The paper addresses an important problem: language models can express high confidence in incorrect answers, which undermines their reliability in practical applications. The proposed separation of intervention timing from the activation-editing mechanism is an interesting approach, and the theoretical analysis provides a useful framework for understanding selective interventions.
Critical weaknesses
-
The paper defines confidence as when the model is asked whether its previous answer is correct. However, this measure could capture the model’s tendency to affirm its own previous answer rather than its actual confidence in that answer. For example, a model might answer "yes" because it tends to defend its previous response, even when it is uncertain. The paper also uses to classify an answer as confident, but this threshold may not reliably distinguish confident from uncertain responses. The authors should provide stronger validation of this proxy and justify the choice of threshold.
-
The paper applies steering to both the initial answer generation and the subsequent YES/NO verification turn. This makes it difficult to determine whether the method genuinely improves confidence calibration or simply changes the model’s tendency to answer "yes." For example, steering might reduce for an incorrect answer without changing the model’s underlying assessment of whether that answer is correct. To address this concern, the authors should include controls that measure confidence without steering the verification turn, or compare the effects of steering on YES/NO responses independently of its effects on the initial answer.
-
The proposed method primarily reduces confidence in incorrect answers, but does not necessarily correct the underlying answers. For example, if the model gives an incorrect answer with , steering reduces this probability to while leaving the original answer unchanged. This could improve calibration-related metrics, but it does not make the answer itself more accurate. The practical value of the method therefore depends on whether reduced confidence leads to useful downstream behavior.
Questions for authors
-
How do the authors validate as a reliable measure of model confidence, and why is 0.5 an appropriate threshold for classifying an answer as confident?
-
How do the authors disentangle genuine improvements in confidence calibration from changes in the model’s tendency to answer "yes," given that steering is applied to both the initial answer and the verification turn?
-
Does reducing confidence in incorrect answers improve practical reliability, even when the answers themselves remain unchanged?
-
How sensitive are the reported results to the choice of confidence threshold and the operational definition of overconfident-wrong answers?
-
Minor issue: The table caption should be placed above the table, not below it.
Response to Reviewer ShQ4
We ran the control you suggested. On Gemma, we held the original answer fixed and steered only the YES/NO verification turn. Selectivity was 0.274, close to the 0.294 we obtained by steering both turns. Steering only the answer gave 0.159. Qwen behaved quite differently. Verification-only steering gave 0.006, while steering the answer alone gave 0.172, the same point estimate as steering both turns. Section 5 now puts these results side by side. Your concern about changing the tendency to say YES explains much of the Gemma result.
We use self-affirmation for the probability the model assigns to YES after normalizing over YES and NO. At 0.5 the model favors neither response. We checked this score against answer correctness and repeated the check with two other readouts. On Gemma MMLU, Brier score improved from 0.372 to 0.294 for self-affirmation, from 0.390 to 0.336 for answer-letter probabilities, and from 0.235 to 0.226 for option verification. All three readouts became better predictors of correctness on Gemma. What the model privately believes remains open. Across cutoffs 0.4, 0.5 and 0.6, PTS had the highest of eight selectivity estimates on Gemma MMLU and prompting led on Qwen. The Gemma comparison against the trace condition had adjusted p = 0.064 at 0.4 and 0.5 in the expanded 21-test family (Appendix P).
In your example, lowering confidence from 0.9 to 0.3 changes the decision if the system can abstain. We evaluated a rule that earns 1 for a correct answer, loses 2 for a wrong one and earns 0 for abstaining. Its acceptance cutoff is 2/3. Across 3,000 Gemma MMLU questions, steering corrected 177 answers and introduced 169 errors. With just eight net corrections, mean utility rose from −0.170 to 0.064. Platt calibration of the original scores did better on this utility (0.087). Steering gave the better risk ranking, lowering area under the risk–coverage curve from 0.305 to 0.280. On Qwen, utility fell from 0.303 to 0.296.
We also tested an outcome that requires the model to give a second answer, without a YES/NO verifier. After a user challenged its first answer, the gated edit preserved 1,142 of 1,242 useful corrections (91.9%). Always keeping the first answer on the very same flagged questions preserved 569 (45.8%). Keeping the first answer prevented more harmful reversals and finished with more correct answers overall. The gated edit, however, preserved 573 more opportunities for the model to accept a valid correction. That difference is visible in the answers themselves (Appendix S.1). We also moved the table captions above the tables as requested.