- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces CAIC, a framework for selecting activation interventions that reduce counterfactual sensitivity of a specified decision score under operational preservation constraints. CAIC-S removes dominant counterfactual displacement directions, while CAIC-T constructs decision aligned directions with penalties for overlap with task relevant contrasts. The framework distinguishes the intervention site from the deployed scoring endpoint, selects configurations on validation data, and reports held out sensitivity bounds.
Experiments include a controlled, bias injected task and semi-synthetic salary screening with two principal 7B models. CAIC-S substantially reduces final output probability gaps, although score compression contributes to these improvements. CAIC-T better preserves several task and score distribution diagnostics at an onsite affine lens endpoint, but its mitigation largely disappears at the native final output.
Critical strengths
-
The distinction between intervention location and deployed scoring endpoint is useful and supported by informative negative results. Table 1 shows that CAIC-T’s onsite improvements do not survive downstream computation. The paper explicitly reports this limitation and abstains at the final-output endpoint rather than presenting intermediate improvements as successful mitigation of the original model.
-
The empirical analysis goes beyond raw counterfactual gaps. It includes matched constraint comparisons with seven white box baselines, neutral CDF quantile gaps, score-dispersion retention, threshold changes, and held out uncertainty estimates. Table 7 shows that CAIC-S’s advantage is not entirely explained by score rescaling. The separation of fitting, selection, and held out evaluation is also a methodological strength.
Critical weaknesses
-
Evidence for practically useful mitigation under adequate preservation remains limited. On the admitted-seed subsets in Table 1, CAIC-S retains only 16.8%–49.4% of neutral-score standard deviation and removes 42.4%–72.0% of the measured task signal. Its admission criteria are primarily ranking-based and therefore tolerate substantial changes in score scale and fixed-threshold decisions. CAIC-T improves this tradeoff, but only through an alternative early-exit affine scorer: final-output reductions are just 0.2%–1.9%, with no final-output configuration admitted in 20 conditions. Onsite admission also varies substantially, including only 1/5 seeds for Mistral race. These findings are transparently reported, but leave the demonstrated deployment benefit narrower than the framework’s motivation.
-
The incremental value of the certification component is insufficiently established. Theorem 1 follows directly from its Lipschitz assumption, the directional bound uses the standard sigmoid Lipschitz constant, and the population bound is an existing empirical-Bernstein result. In the evaluated finite-family setting, computing the directional certificate uses the same counterfactual representations from which the exact score gaps can already be obtained. The paper distinguishes mean and maximum aggregation correctly, but does not convincingly demonstrate when the directional certificate enables a useful guarantee or operational decision beyond direct held-out gap estimation with a population UCB. I view this primarily as a limitation of contribution and demonstrated usefulness, rather than an identified mathematical error.
Questions for authors
- Within the existing candidate sweeps, what happens if CAIC-S and the strongest baselines are selected under common score-dispersion and fixed-threshold preservation requirements, in addition to utility and specificity? Does CAIC-S retain an advantage in quantile-gap reduction at comparable preservation levels?
- At the same frozen affine-lens endpoint, how does CAIC-T compare with CAIC-S and representative erasure baselines under identical admission requirements? This would help establish how much of the favorable tradeoff comes from the task-protected operator rather than the change of scoring endpoint.
- Can the authors identify a concrete case in the reported experiments where the directional certificate provides actionable information beyond the exact finite-family gap and its empirical-Bernstein UCB? Does it provide coverage beyond the explicitly evaluated counterfactuals under assumptions actually verified in these experiments?