- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces LOTUS, a framework for hallucination detection using compact representations of LLM hidden states. The method summarizes token activations through peak values, quantiles, and cross-layer differences, then applies Tucker-2 projections and a random-forest classifier. Experiments across two LLMs and four QA benchmarks demonstrate competitive detection performance with reduced representation storage.
Critical strengths
- The proposed framework is simple and well motivated, producing compact representations while incorporating information across layers and token positions.
- LOTUS consistently outperforms HARP and remains competitive with ACT-ViT across the evaluated settings. The summary ablations and cross-model alignment experiments provide additional insight into the method’s behavior.
Critical weaknesses
-
Limited methodological contribution. LOTUS combines established statistical summaries, Tucker-2 decomposition, and a random-forest classifier. While practically useful, the current evidence does not sufficiently establish the advantage of the proposed multilinear structure over simpler alternatives. The paper reports that equal-dimensional PCA performs within 0.80 AUROC points with full training data, while single-summary variants often remain close to the full method.
-
Practical efficiency. Reduced projection size and representation storage do not directly establish lower runtime or peak memory. A matched comparison of activation extraction, projection fitting, and detector inference would help substantiate the efficiency claim and distinguish offline costs from per-response overhead.
-
Interpretation of the spectral analysis. The analysis supports compressibility but does not directly establish that the retained directions preserve the most useful information for hallucination detection. The connection between variance preservation and discriminative performance should be supported more directly or stated more cautiously. \end{itemize}
Questions for authors
-
With summaries, layers, classifier, and output dimensionality held fixed, what advantages does Tucker-2 provide over flat PCA in detection performance and computational cost?
-
How sensitive are the results to the number of sampled responses ? Since affects both training-set size and the identification of model-known questions, separating these effects would help assess the robustness of the evaluation protocol.
-
Can the authors compare detection using the retained subspace with detection using the discarded residual, to establish whether the low-rank projection preserves the relevant discriminative information?
Unless I have overlooked supplementary material, the version available to me does not include the appendices referenced in the main text. Could the authors clarify where these can be accessed? I would be happy to reconsider my score if the additional material and author response adequately address my concerns.
4 comments
Response to Reviewer zjPm (2/2)
W3 / Q3. Detection with the retained subspace versus the discarded residual.
New, Appendix R. For each summary , the residual is . The same random forest is trained on four inputs:
- the retained Tucker-2 core;
- a Tucker-2 core of at the same ranks (896 features);
- a random projection of to 896 features;
- the retained and residual cores together.
Pooled AUROC (%), mean ± std over 5 seeds; within-question AUROC in brackets.
| Qwen TQA | Qwen TyDi | LLaMA TQA | LLaMA TyDi | |
|---|---|---|---|---|
| Retained (LOTUS) | 87.76 ± 0.9 [82.1] | 87.82 ± 2.0 [88.1] | 89.22 ± 1.4 [82.7] | 82.47 ± 1.2 [81.3] |
| Residual, Tucker-2 core | 86.34 ± 0.9 [80.1] | 86.77 ± 2.1 [88.2] | 88.87 ± 1.2 [81.7] | 82.05 ± 1.4 [80.8] |
| Residual, random projection | 76.43 ± 1.1 [74.0] | 80.10 ± 2.0 [83.0] | 79.08 ± 1.1 [73.8] | 72.71 ± 3.0 [70.6] |
| Retained + residual | 87.45 ± 0.7 [81.2] | 87.48 ± 2.0 [87.9] | 89.30 ± 1.2 [82.7] | 82.55 ± 1.2 [81.4] |
- Nothing usable is discarded. Adding the residual to the retained core changes AUROC by −0.34 to +0.08 points, within one seed standard deviation.
- The retained directions are the best slice. The retained core exceeds the residual's best same-size core in all four settings, by 0.35–1.42 points.
- The signal is redundant. The residual's leading directions remain informative, whereas a random projection of the residual lowers AUROC by 7.7–11.3 points. The hallucination signal is therefore distributed redundantly across many directions. This redundancy is why a low-rank projection loses nothing.
The revised spectral paragraph states that the spectra establish compressibility and that this experiment provides the evidence on discriminative content. Consistent with it, increasing the feature rank from 64 to 128 changes AUROC by at most 0.46 points (Table 13).
Q2. Sensitivity to the number of sampled responses K.
New, Appendix S. For k ∈ {5, 3}, a seeded random k of the 10 responses per question is drawn. Three variants then change one factor at a time:
- training-set size only: model-known questions and the split come from all 10 responses;
- identification of model-known questions only: from the k responses, keeping every response;
- both: the protocol as if K = k had been sampled.
Pooled AUROC (%), change from K = 10 in parentheses.
| Qwen TQA | Qwen TyDi | LLaMA TQA | LLaMA TyDi | |
|---|---|---|---|---|
| K = 10 (reported) | 87.76 | 87.82 | 89.22 | 82.47 |
| Training size only, k = 5 | 87.18 (−0.59) | 87.10 (−0.73) | 88.64 (−0.57) | 80.97 (−1.50) |
| Training size only, k = 3 | 86.75 (−1.01) | 87.29 (−0.54) | 87.82 (−1.40) | 80.42 (−2.05) |
| Identification only, k = 5 | 87.50 (−0.26) | 86.66 (−1.16) | 88.62 (−0.60) | 81.95 (−0.52) |
| Identification only, k = 3 | 87.53 (−0.24) | 85.36 (−2.47) | 85.92 (−3.29) | 80.27 (−2.20) |
| Both, k = 5 | 87.55 (−0.21) | 85.19 (−2.63) | 89.13 (−0.09) | 82.34 (−0.13) |
| Both, k = 3 | 87.71 (−0.05) | 84.47 (−3.36) | 85.84 (−3.37) | 81.13 (−1.35) |
- With k = 5, each factor alone changes AUROC by at most 1.50 points. The full protocol stays within 0.21 points in three settings and is 2.63 points lower on Qwen/TyDiQA-GP, the smallest dataset (seed standard deviation 2.0). 5–8% of model-known questions are no longer identified.
- With k = 3, 11–17% of model-known questions are no longer identified. Identification becomes the larger factor, lowering AUROC by up to 3.37 points.
The protocol is therefore stable down to five responses per question. Appendix S reports the known-question counts and train/test sizes for every row.
We hope these additions address the reviewer's concerns, and we would be grateful if the reviewer would reconsider the assessment.
I thank the authors for their detailed responses and the comprehensive experimental results presented in the rebuttal. Although I remain unconvinced that Tucker2 offers a significant advantage over simpler clustering methods, the paper provides useful insights into the effectiveness of low-rank multilinear decomposition for hallucination detection. I have therefore decided to raise my score from 2 to 3.
We thank the reviewer for engaging with the new results and for raising the score. We agree that, with all training data, Tucker-2 does not outperform simpler reductions: it matches flat PCA (Table 8). The revised paper therefore states its advantages as about 40 times fewer fitted parameters and a lead over flat PCA that averages 0.9–2.7 AUROC points when 5–50% of the labelled training questions are available (Table 11), not higher accuracy with all labels.
Response to Reviewer zjPm (1/2)
We thank the reviewer for the detailed review and for the offer to reconsider. We apologize for the missing appendices: they were in the supplementary material (Appendices A–Q). The revised PDF now includes them after the references, together with new Appendices R–W. Table and appendix numbers below refer to the revised PDF, and each new result is given here in full.
W1 / Q1. Advantage of Tucker-2 over flat PCA with summaries, layers, classifier and width fixed.
Table 8 reports exactly this comparison: the same summaries, layer window, random forest and 896 output features (pooled AUROC, %).
With full training data, the two reductions are within 0.80 AUROC points. The multilinear structure does not improve accuracy in this regime, and the revised text states this.
Tucker-2 requires about 40× fewer fitted parameters and 4.6× fewer multiply-adds per response.
With fewer labelled questions, Tucker-2 is more accurate (Table 11). At 25% and 50% of the training questions, where flat PCA can still supply all 896 components, Tucker-2 improves AUROC over flat PCA in 3 of 4 settings, by 0.71–2.91 points.
The fitted bases matter: a random projection of equal width lowers AUROC by 2.44–5.23 points.
Measured cost (new, Appendix V; TruthfulQA, 8 CPU cores, Qwen / LLaMA):
The smaller projection therefore does not reduce runtime or memory at this scale, where robust scaling of the summaries dominates both. The revised text states the advantage as model size and robustness to scarce labels.
Against the strongest supervised baseline, the same property shows more clearly (new, Appendix T): with 5–10% of the training questions, LOTUS exceeds ACT-ViT by 4.42–28.22 AUROC points in all four settings.
On single-summary variants: we agree that each summary alone comes close to the full method. The full configuration is the most consistent, being the best or within 0.74 points of the best variant in every setting (Table 3). The revised text claims no more than this.
W2. Runtime and peak memory, offline versus per response.
New, Appendix V. TruthfulQA; one H100 for GPU stages and 8 CPU cores otherwise; Qwen / LLaMA.
The forward-pass times vary between runs on shared nodes, so we give the range over two runs. The cost profile is mixed:
The revised paper reports this profile in full instead of storage alone.