- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
Authors provide a way to estimate epistemic uncertainty by training draft models which are trained on disjoint partitions of the training dataset, along with a distillation setup to predict the mean of the target predictive distribution. The estimates are tested against predicting Gaussian-induced uncertainty in a sandbox environment, as well as hallucination detection in GSM8K and ASQA. Theory is provided to show that the estimate is grounded.
Critical strengths
- The proposed method is straightforward, although understanding the actual algorithm is difficult in the current flow (see weaknesses).
- The connection between the proposed decomposition and bias/variance is elegant.
Critical weaknesses
- Overall, the paper is difficult to follow and poorly written. In the theory section there are multiple incidents of missing or undefined notation, and although I could piece together what was meant in most cases this should not be the job of the reader. Even in the first equation in 2.1 although I inferred that this is decomposition of total uncertainty into aleatoric and epistemic, the presentation is extremely unclear. If I were a practitioner attempting to use this method I would come away from this paper frustrated and less likely to want to attempt to reproduce these results.
- Comparisons with other methods need much more context. Neither semantic entropy or KLE are discussed in any detail but just tossed into a results table. KLE is not even cited in the references. I would consider these types of omission grounds for desk rejection.
- No discussion is provided around why a token-based approach is outperforming semantic methods like semantic entropy which take the entire output into account. This result feels not very believable and many more ablations need to be performed.
- No discussion around why hallucination detection is even a reasonable task for an epistemic uncertainty paper, given that it's unclear that hallucinations are purely epistemic.
- Unclear how the scales of the Gaussian noise were selected to generate the ground truth in the sandbox experiment. I remain unconvinced that using a simple Gaussian to generate targets is warranted, and the appendix section attempting this justification is near indecipherable. It seems that there is an attempt to use the Laplace approximation to justify use of Gaussians to estimate the predictive posterior but given that there are very few implementation details on what the scale of these Gaussians are in the main text this entire explanation feels very jumbled and confusing.
- Table 2 results are very unconvincing. In many categories the proposed method does quite poorly relative to baselines.
Questions for authors
Please see the comments in weaknesses above. All of these have to be addressed, but the main issue is that the paper basically needs to be rewritten with a much clearer narrative and much more intuitive discussion of the results before I would consider it acceptable at any conference, let alone ICLR. Currently the paper feels like a raw dumping of results without much context.
In general, it feels like LLM usage was very heavy in preparation of this manuscript, given that there is a lot of technical output without much actual insight or explanation. Can authors confirm exactly how much LLM usage was involved in preparation of this manuscript and explain the insights in every single piece of theory that was presented?
5 comments
How the baselines differ. Semantic Entropy groups sampled responses by semantic equivalence and measures uncertainty across those groups. KLE uses a semantic-similarity kernel and von Neumann entropy to represent finer relationships between responses. Our method instead measures differences between conditional next-token distributions at shared prefixes. Semantic Entropy, KLE.
These methods are relevant comparisons because they use uncertainty to identify unreliable generations. Table 2 evaluates their downstream detection utility; it does not assume that they estimate an identical mathematical quantity.
Settings for the additional evaluation below. The saved configurations use ten auxiliary responses per question, sampled at temperature and top-, for both semantic baselines. Evaluated target responses were sampled separately at temperature and top-, with a maximum of 2,048 generated tokens. Semantic Entropy uses empirical cluster frequencies, with normalized-answer matches and pairwise SAME/DIFFERENT judgments from the Qwen3-8B-Instruct checkpoint. KLE uses microsoft/deberta-large-mnli probabilities, combining entailment and half the neutral probability, symmetrized across directions. It uses a heat kernel with parameter , an unnormalized graph Laplacian, and unit-trace kernel normalization; the NLI pairs exclude the question prompt. Calibration and evaluation settings are specified in Response 3. These settings describe the additional Table A evaluation. We will consolidate the baseline details and timing boundaries in the manuscript.
3. Token-Level Scoring, Semantic Baselines, and Additional Ablations
The comparison asks whether token-distribution scoring offers a useful alternative to methods requiring sampled responses and semantic processing. In submitted Table 2, the measured 1×3 evaluation is much faster than Semantic Entropy and KLE; its ASQA mean AUROC is above Semantic Entropy's and below KLE's. The appropriate interpretation is a measured detection–latency trade-off. The additional 2×3 analysis below separately tests component contribution and response-length effects; it is not a new timing experiment.
What token-level scoring observes. "Token-level" describes the resolution of the score: each distribution is conditioned on the complete available prefix, and the response score aggregates across generated positions. One hypothesis is that local predictive disagreement or mismatch captures instability associated with an incorrect response. Semantic methods instead measure variation across the meanings of sampled responses. Our experiments do not establish which mechanism explains their relative performance, and summing token scores can introduce a response-length effect.
Completed post-processing analysis. We compared Full EU, JSD-only, and KL-only using both sum and mean aggregation, alongside length-only and the saved UQ baselines. For a response with retained scored positions, the aggregations are
We also fitted mean-score-plus-length controls. Semantic Entropy and KLE were counted once per response, rather than summed across their repeated token rows.
Additional evaluation protocol. Table A uses saved Llama-3.1-8B-Instruct responses scored by six Llama-3.2-1B-Instruct drafts in the 2×3 configuration, with a generation budget of 2,048 tokens and generation seeds 0–2. Original labels and length-capped responses are retained. Length is the number of retained scored positions. We used a shared 80/20 question-grouped split across seeds, so all responses to the same question remain in one partition. Every method is evaluated on identical test responses within each dataset. The held-out sets contain 792 responses to 264 GSM8K questions and 569 responses to 190 ASQA questions.
Each row uses a separate logistic regression with training-only standardization, fitted to pooled training responses across seeds. Score direction is determined from training data only. This additional analysis differs from submitted Table 2, which used the 1×3 configuration, in ensemble configuration and evaluation protocol; numerical comparisons should be made within each table.
Table A. Length and Score-Component Ablation
Values are AUROC mean ± sample SD across three fixed-checkpoint generation repetitions, not independent retrainings. AUROC uses predicted error probabilities; ASQA error means hallucinated. Mean-score-plus-length rows use two-feature classifiers.
| Method | GSM8K AUROC ↑ | ASQA AUROC ↑ |
|---|---|---|
| Full EU (sum) | 0.716 ± 0.012 | 0.618 ± 0.019 |
| Full EU (mean) | 0.673 ± 0.025 | 0.572 ± 0.048 |
| JSD-only (sum) | 0.691 ± 0.022 | 0.520 ± 0.038 |
| JSD-only (mean) | 0.603 ± 0.006 | 0.580 ± 0.029 |
| KL-only (sum) | 0.715 ± 0.012 | 0.619 ± 0.019 |
| KL-only (mean) | 0.673 ± 0.026 | 0.574 ± 0.049 |
| Length-only | 0.642 ± 0.037 | 0.566 ± 0.028 |
| TokUR (sum) | 0.704 ± 0.009 | 0.609 ± 0.032 |
| TokUR (mean) | 0.654 ± 0.035 | 0.574 ± 0.042 |
| Semantic Entropy | 0.816 ± 0.005 | 0.586 ± 0.017 |
| KLE | 0.667 ± 0.037 | 0.685 ± 0.012 |
| Full EU (mean) + length | 0.716 ± 0.007 | 0.609 ± 0.029 |
| KL-only (mean) + length | 0.716 ± 0.008 | 0.610 ± 0.030 |
Selected Paired AUROC Differences
Intervals are 95% percentile intervals from 2,000 paired question-cluster bootstrap samples, with each question resampled jointly across methods and seeds. The statistic is the mean per-seed test AUROC. The fitted classifiers and split remain fixed, and the intervals are not adjusted for multiple comparisons. The selected contrasts address component contribution, aggregation, and information beyond length.
| First − second | GSM8K difference [95% CI] | ASQA difference [95% CI] |
|---|---|---|
| Full EU (sum) − KL-only (sum) | 0.0005 [-0.0001, 0.0013] | -0.0011 [-0.0022, -0.0001] |
| Full EU (mean) − KL-only (mean) | 0.0000 [-0.0011, 0.0010] | -0.0022 [-0.0039, -0.0006] |
| Full EU (mean) − Full EU (sum) | -0.0428 [-0.0820, -0.0069] | -0.0455 [-0.1055, 0.0126] |
| [Full EU (mean) + length] − Length-only | 0.0736 [0.0237, 0.1259] | 0.0423 [-0.0405, 0.1203] |
| [Full EU (mean) + length] − [KL-only (mean) + length] | -0.0002 [-0.0010, 0.0007] | -0.0017 [-0.0031, -0.0002] |
Interpretation. The length-controlled analysis identifies useful error-related information on GSM8K. Adding Full-EU mean to length improves AUROC over length alone by 0.0736, with 95% interval [0.0237, 0.1259]; KL-only gives a comparable improvement. Semantic Entropy has the highest mean GSM8K AUROC (0.816), and KLE leads on ASQA (0.685). The corresponding Full-EU-plus-length versus length-only interval on ASQA includes zero. These results establish the scope of the detection signal under this additional protocol; its cost–performance balance requires its own matched timing measurements.
Component contribution. Adding disagreement to KL-only changes sum-score AUROC by 0.0005 on GSM8K, with an interval containing zero, and by -0.0011 on ASQA. Mean aggregation likewise gives no consistent incremental detection benefit. We will therefore distinguish the algebraic decomposition from an empirical claim that both terms are needed for detection. This component result limits the claim for the combined score; the separate comparison with expensive uncertainty estimators concerns the cost and utility of draft/proxy scoring as a whole.
4. Why Hallucination Detection Is Relevant to Epistemic Uncertainty
Hallucination detection is an operational use of an uncertainty score, rather than a ground-truth measurement of EU. A model may consistently give an incorrect answer with low disagreement, and high uncertainty need not imply factual error. We therefore evaluate reference-EU fidelity and downstream detection as separate questions.
The two experiments answer separate questions. Table 1 measures fidelity to the uncertainty of a specified teacher family. Table 2 evaluates whether the resulting score helps identify incorrect or hallucinated responses. Downstream detection performance does not establish that the teacher reference is a calibrated Bayesian posterior.
We will make this distinction explicit and qualify the introduction's stronger language connecting EU to hallucinations. We will also clarify the operational labels: GSM8K evaluates final-answer correctness, whereas ASQA uses judge-assigned hallucination labels. Under the submitted ASQA policy, non-hallucinated responses include supported, abstained, and incomplete responses, so non-hallucination should not be equated with strict answer correctness. These evaluations provide evidence of practical utility within their respective protocols.
5. Gaussian Perturbation Scale and Its Posterior Interpretation
Thank you for highlighting this ambiguity. We agree that the perturbation-scale selection and its relationship to the posterior interpretation need to be explained more clearly.
Response to Reviewer 2Sfs
We thank the reviewer for the detailed feedback. The central question is whether a lightweight draft ensemble and a learned predictive-mean proxy can approximate a specified teacher family's token-level uncertainty while providing a useful detection–latency trade-off. We assess this through reference fidelity and downstream detection, with computational measurements reported separately. Submitted Table 2's 1×3 configuration reports a GSM8K mean AUROC of 0.768 versus 0.765 for TokUR. Separately, ASQA profiling measures 0.783 versus 0.890 s per batch, with substantially larger latency differences relative to Semantic Entropy and KLE. Below, we clarify the theory, report the component and length controls, and specify where this trade-off holds. We also acknowledge the missing KLE citation and will add it.
1. Clarity of Notation and the Insights Behind the Theory
The theory addresses a practical transfer question: which aspects of a teacher ensemble must the drafts approximate to preserve its uncertainty? Matching only the predictive mean can erase disagreement, whereas teacher-specific predictive fidelity provides a sufficient condition for finite-reference EU transfer. We will introduce the notation and organize the results around that distinction.
Definitions and uncertainty decomposition. At generation step t, fix the shared prefix ht=(x,y<t). Let pθ,t=pθ(⋅∣ht) denote a teacher model's next-token distribution over the vocabulary, let πT denote the specified teacher-parameter reference distribution, and let pˉT,t=Eθ∼πT[pθ,t]. The uncertainty decomposition is
H(pˉT,t)=Eθ∼πT[H(pθ,t)]+I(Yt;θ∣ht).
Here, H denotes categorical entropy and Yt is the next-token random variable. The left-hand side is total predictive uncertainty. The first term on the right is the aleatoric component, measuring uncertainty within individual teacher predictions. The second is the epistemic component relative to πT, measuring predictive variation across the teacher reference. Its interpretation depends on the choice of πT.
The practical draft score. For K draft predictions, define qmix,t=K1∑k=1Kqk,t, and let pmix,t denote the learned proxy for the teacher predictive mean. All distributions are evaluated at the same prefix and over a common vocabulary. Our full score is
utfull=JSD(q1,t,…,qK,t)+KL(qmix,t∥pmix,t).
The first term measures disagreement among drafts; the second measures mismatch between their mean prediction and the proxy reference. A scored draft prediction may itself be a group-averaged prediction, as specified by the ensemble configuration.
What each theoretical result contributes.
We will reorganize the theory around these questions, define notation before its first use, and place each result's intuition and assumptions alongside its statement. We will also distinguish the token-level definitions from the operational aggregation used for downstream detection. Summing scores along a generated response does not automatically produce sequence-level mutual information.
2. Context and Citation for Semantic Entropy and KLE
The missing KLE reference is an omission, and we apologize for it. We will add Nikitin et al., Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities, NeurIPS 2024, and expand the discussion of both semantic baselines.