- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper investigates the relationship between estimated aleatoric and epistemic uncertainty proxies in an architecture where the two are learned separately. It investigates the setting with a concept-bottleneck model, where the relevant uncertainties are given direct supervision targets. The authors provide an empirical study of how these learned uncertainties correlate to each other as well as to the model's errors. The paper includes ablation studies on various possible design choices.
Critical strengths
The high-level idea investigated that aleatoric and epistemic uncertainty should in principle not necessarily be correlated is an intuitive and interesting topic of study.
Within the framework considered, the paper does a good job on reporting the empirical evaluations, clearly addressing which experiments provide evidence for which claims and the limitations involved.
Critical weaknesses
The paper is framed as an investigation into the relationship between aleatoric and epistemic uncertainty estimates. However, a critical concern is that the quantity that the authors use as the epistemic head's regression target is more closely related to total error or uncertainty than epistemic uncertainty. The authors point out this limitation (lines 204-205), but it is in my view a critical mismatch of what is being presented as investigated. The notation (EU, etc.) strongly suggests that the authors are indeed presenting the findings as concerning to what is commonly understood as epistemic uncertainty. The lack of a clear regression target is part of what makes epistemic uncertainty estimation challenging, and using residual error as a proxy for this does not faithfully capture the key behavior of epistemic uncertainty. This choice is not sufficiently motivated and it does not appear sound to me to characterise this as an "epistemic head" regression target.
Following on from the point above, it becomes unclear what the interesting scientific results from the presented experiments are. The relationship between error and EU (which the authors claim "carries signal" in the abstract) is entire given the regression objective is directly derived from error. The authors argue that their results suggest that low correlation does not imply a faithful semantic representation of aleatoric and epistemic uncertainty. Unfortunately, this negative result is only demonstrated for the specific setting and definitions addressed in this particular paper, which as argued above is of questionable relevance to the broader research community, and with no quantitative comparison with other methods that investigate the relationship/correlation between aleatoric and epistemic uncertainty.
Questions for authors
Clarification requests:
- Is there further formal justification for interpreting the error regression target as appropriate for an "epistemic"?
- If I am understanding the results in Table 1 correctly, I would expect AU and EU to be positively correlated (assuming no decorrelation penalty). This is because under a well-fitted regression, higher EU (as defined in the paper, i.e. through regressing against residual error) would usually be expected to be present in those samples where labels are ambiguous. However, the correlations here are low or negative. Is my understanding correct and why is this the case?
Further questions/future work:
- Why is AU nearly constant with no supervision? If it is the output of an untrained NN head I would still expect there to be variation in the output due to changing input.
5 comments
Why is the ambiguity output nearly constant without supervision? An untrained neural head can vary with its input. Our CEBaB ablation removes both direct ambiguity-supervision terms and measures the resulting dispersion. Figure 2 and Appendix H show that the score's standard deviation is below from the first recorded epoch: the first-epoch validation dispersions are , , and across the three seeds (versus at epoch 1 for the supervised configuration), with selected-checkpoint test dispersions of , , and , respectively, which we recomputed from the saved prediction arrays; the logged training and validation losses are finite. We also audited the saved ablation checkpoints to examine the candidate causes:
- The ambiguity MLP never trained: In every ablation run, every layer's weights remain inside their default-initialization support ( of weights exceed the Kaiming-uniform init bound in any layer or seed; the layer RMS values only shrink, from at initialization to ), which is the signature of weight decay on parameters no loss reaches.
- Bias drift via weight decay: The learnable offset drifts to the same value on all four concepts ( at the seed- checkpoint, at the seed- checkpoint, at the seed- checkpoint), with displacement proportional to the selected epoch () — the exact behaviour of the decoupled weight decay in the AdamW optimizer (), since removing the ambiguity losses cuts the gradient paths to this bias.
- Input projection movement: The input projection supplying the head is the only component that demonstrably moves beyond initialization (up to the init bound; of its weights outside the init support), consistent with the orthogonality penalty, which our gradient audit shows is the largest-magnitude term reaching that projection.
The supervised checkpoints show the contrast: of MLP weights and of projection weights move beyond init bounds. No initialization-state checkpoint exists (each checkpoint stores only the selected epoch's parameters and validation metrics), so we cannot recover pre-update dispersion from these artifacts; but the forensics above narrow the open question to the state of a head whose nonlinear weights demonstrably never moved beyond their initialization distribution. We restrict the initialization claim to the recorded observations. A matched rerun with a step-0 dump would measure the pre-training state directly.
We use as an operational near-constancy threshold. A nonconstant score can have a mathematically defined rank correlation even below this threshold; withholding it does not prove that its ranking is uninformative. (For the three matched HateXplain runs the audit-only rank correlations are , , and , consistent with a constant output rather than an informative ranking.)
Dear Reviewer as the author-reviewer discussion period ends soon we kindly request that you read the rebuttal and confirm whether your concerns are addressed. We remain committed to answering any further questions you have.
Response to reviewer RrWL
We thank the reviewer for their comments. We address their queries below. Appendix E establishes the distinction between the residual target and ideal epistemic uncertainty. We make that distinction explicit here, then use the saved-checkpoint diagnostics to answer the questions about score correlation and near-constant outputs.
Why use the term epistemic? The absolute residual is not a justified target for the ideal epistemic quantity in Equation 1. For a binary label Y∼Bernoulli(q) and a correct predictor p=q,
\qquad D_{\mathrm{KL}}\!\left(\operatorname{Bernoulli}(q) \,\|\, \operatorname{Bernoulli}(q)\right) = 0.$$ The residual therefore retains a component due to label uncertainty. Our clipped and regularized regression does not remove this component. We use “residual-based score” for the learned output and reserve the epistemic interpretation for the ideal quantity or an explicitly tested hypothesis. **Scientific scope and comparisons.** We study what separate supervision and direct gradient isolation establish about the learned scores. Proposition 4.1 concerns direct loss derivatives; it does not imply statistical independence or semantic validity. On CEBaB, the two scores correlate weakly without a decorrelation penalty ($-0.14$ and $0.00$), while the ambiguity scores correlate with annotation entropy at $0.22$ and $0.24$ (ambiguity output and entropy both averaged over annotated aspects only; the naive all-aspect values are $0.03$ and $0.06$, and the concept-level binary-labelled value is $0.31/0.31$ — we will report the mask with each number). The residual score's task-error AUROC is $0.72$, below confidence at $0.78$ and $0.79$. Fitting concept residuals does not guarantee alignment with held-out task errors. The observed alignment measures downstream utility; we do not treat it as evidence of a purely epistemic signal. The additional ensemble analysis reports correlations of $0.73$ and $0.52$ between mutual information and expected entropy. Expected entropy correlates with task annotation entropy at $0.44$ and $0.47$. These results compare conventional uncertainty components and require us to interpret dependence alongside the target and evaluation task. They do not establish why the residual-based construction gives different correlations, and the different ambiguity targets preclude a direct ranking of the two methods' alignment coefficients. **Why are residual and ambiguity scores not positively correlated?** Your expectation holds in the idealized setting of Appendix E. If $p(x) = q(x)$, the population squared-loss regressor of the raw absolute residual outputs $2q(x)(1 - q(x))$. For distinct $q$ values in $(0, 1/2)$, this quantity and Bernoulli entropy have identical rankings. Their Spearman correlation is therefore one. We computed the requested decomposition on a common held-out mask, per concept, before and after aggregation, and separately for binary-labelled and annotated-nonbinary aspects. The decomposition identifies the principal empirical differences: * **Binary-labelled concepts ($n = 3,058$ concept-annotation pairs):** The actual transformed residual target correlates with annotation entropy at only $0.15$ (DistilBERT) and $0.18$ (RoBERTa-base) — the targets themselves are far from rank-equivalent. The scale output aligns with its own target at $0.69/0.72$ ($\text{RMSE } 0.50/0.41$); the ambiguity output correlates with entropy at $0.31/0.31$ pooled ($0.33/0.35$ review-level); and the two learned outputs correlate with each other at $0.09/0.22$ pooled. * **Annotated-nonbinary aspects (unknown majority, $n = 1,876$):** The auxiliary loss trains the ambiguity head toward the constant target $1$ ($\text{RMSE } 0.42/0.46$) and its entropy correlation inverts to $-0.14/-0.16$ ($-0.13/-0.13$ review-level). * **Per-aspect (binary):** Food $0.31$, service $0.21$, ambiance $0.33$, and noise $0.26$ for DistilBERT; and $0.31/0.17/0.35/0.31$ for RoBERTa-base. The observed low score correlations therefore arise from three identifiable sources — target non-equivalence ($\rho(\text{target}, H) \approx 0.15\text{–}0.18$), differing supervision masks (the constant-$1$ pull on unknown-majority aspects, which inverts the correlation), and partial target fitting — rather than from successful separation; and the Bernoulli example's $\rho = 1$ applies to neither actual target. This decomposition replaces the single pooled correlation in our response; we will incorporate it into the manuscript.