- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2(+1)
Read review
Paper summary
This paper investigates whether query–key (QK) representations in the large language models contain useful signals for verifying the correctness of generated reasoning solutions. The authors propose extracting raw QK inner-product margins between two explicit verdict options, indicating that a candidate solution is either correct or contains an error. The paper proposes two main verification approaches: CF-QK and L2-QK, and conducts experiments on Qwen3 models and DeepSeek-R1-Distill-Llama-8B to demonstrate improvements over verdict logits and other scalar verification baselines on MATH-500 and an adapted HLE benchmark. Overall, the paper presents an interesting approach to extracting verification signals from frozen model representations, supported by reasonably extensive empirical evaluation.
Critical strengths
- A simple and effective verification approach with minimal supervision. The proposed QK-based methods is simple, without fine-tuning or training the models. The experiments also demonstrate the effectiveness of the methods.
- Careful empirical analysis beyond benchmark-level accuracy. The paper provides analyses that strengthen the empirical contribution in different aspects.
Critical weaknesses
The main weakness of this paper lies in its writing, where the sentences and logical flow are extremely difficult to follow. After reading this paper, I'm pretty sure that it was written almost entirely by AI, with little careful human reviewing and polishing. The reasons are as follows:
- Terrible introduction. In the introduction, the background and motivation are not clearly explained, making the paper extremely difficult to follow. Specifically, the first paragraph of the introduction does not clearly explain what "evaluating generated mathematical solutions" actually means, while the second paragraph abruptly shifts to QK alignment without any proper transition or background explanation. Such a logical progression makes the paper very frustrating to read. Furthermore, the authors do not provide a clear explanation of their proposed method before directly moving to the contributions. The standalone "1.1 Contributions" subsection also appears very weird without a subsequent "1.2".
- Lack of clear design principles in the methodology. When introducing the proposed method, the authors provide little explanation of the underlying design principles and motivations, instead directly piling up mathematical formulas. Moreover, the sentences are unusually awkward and rigid, making the methodology difficult to understand.
- Extremely disorganized analysis of experimental results. In Sections 3, 6, and 7, the analysis contains a large number of raw numerical results, frequently interspersed with references to the appendix, making it difficult for readers to focus on and reflect upon the experimental findings. Furthermore, the paper is filled with numerical results but lacks sufficient summarization and synthesis of the general conclusions that can be drawn from them.
Overall, I believe the writing of this paper falls below the acceptable standard for a research paper. In my view, an academic paper should prioritize a clear and systematic presentation of the research problem and limitations of existing approaches, the core principles underlying the proposed methodology and experimental design, and the evidence supporting the conclusions. Rather than piecing together various facts and results through extremely disorganized and awkward sentences.
Questions for authors
First, regarding my assessment that this paper was written almost entirely by AI, with little careful human review or polishing, I would like the authors to honestly answer the following questions:
- What's the proportion of this paper has actually been carefully reviewed by humans? If the proportion is greater than 0, please specify exactly which parts of the paper have undergone human review.
- Were humans sufficiently involved in conducting the experiments in this paper, or were the experiments entirely carried out by AI?
Second, I have the following concerns regarding the paper itself. I hope the authors can carefully revisit their own work and the manuscript, reflect on these issues in depth, and provide their responses.
- The title and task formulation of the paper focus on reasoning verification. However, the main analysis and experiments seem to primarily evaluate final answer correctness. These two concepts are fundamentally different. Could the authors clarify this gap and explain to what extent the proposed method is actually performing reasoning verification rather than outcome verification?
- The evaluation is conducted on a relatively limited set of models, which may not fully reflect the capabilities of current frontier reasoning models. Could the authors include experiments on more recent and stronger models (e.g., Qwen3.5)?
- Could the authors evaluate the proposed analysis and method on non-mathematical reasoning benchmarks? It would be valuable to understand whether the observed QK verification signals and the proposed methods generalize beyond mathematical reasoning tasks.
- The L2-QK method uses only 50 calibration examples. Given that the approach operates over a large number of attention heads and requires learning an ensemble of QK features, it is unclear whether such a small calibration set is sufficient to obtain stable and reliable estimates. Could the authors provide further analysis or discussion regarding calibration data requirements, robustness, and scaling behavior?
8 comments
Rebuttal 2/3
W3: Analysis of experimental results.
A: Sections 3, 6, and 7 (pp. 3, 6–9) now lead with the experimental questions and conclusions. Section 3 follows a multiple-choice example showing how a head’s preference can differ from the model’s output. Section 6 separates verification without labels, verification with 50 labels, and transfer, including model-dependent exceptions. Section 7 explains what each analysis establishes. In particular, ranking an intact reasoning trace above a corrupted one is different from classifying both correctly at a fixed threshold. Detailed comparisons remain in the tables and appendices.
Q3: Does the method verify reasoning or merely outcomes?
A: The primary benchmark labels assess final-answer correctness, while the verifier reads the complete candidate solution (§5). We test sensitivity to intermediate reasoning separately in §7.3 and Appendices C.1–C.2. First, we modify an intermediate equality in 40 MATH solutions per model while preserving the problem and final answer. One-pass CF-QK ranks the intact solution above the edited one in 70% of pairs for Qwen3-8B and 85% for Qwen3-14B. At the fixed zero threshold, classification accuracy on the intact and edited solutions is 51.25% for Qwen3-8B and 58.75% for Qwen3-14B. Second, with the final answer again held fixed, we test 24 erroneous reasoning edits and 16 validity-preserving rewrites. On both models, CF-QK accepts the original and rejects the edit in all 24 error pairs, and accepts both versions in all 16 valid pairs. The results also hold when we remove the explicit final-answer declaration. Direct verdict logits give the same counts. These paired tests show that QK scores can respond to a change in the reasoning even when the final answer stays the same.
Q4: Can you evaluate newer and stronger models, such as Qwen3.5?
A: To address the request for stronger models, we extended our evaluation to Qwen3-Next-80B on MATH and HLE. Like Qwen3.5, this model combines Gated DeltaNet blocks with full-attention layers. It has 80B total parameters. Our readout compares a query at the verdict position with keys at the two verdict options. We evaluate all 192 heads in its 12 full-attention layers.
Table 23. Qwen3-Next-80B verification. AUROC and BA (%). Bold marks the highest value in each metric column.
| Method | MATH AUROC | MATH BA | HLE AUROC | HLE BA |
|---|---|---|---|---|
| CF-QK, batch reference | 91.70 | 83.46 | 85.27 | 81.72 |
| CF-QK, source-frozen | 89.92 | 85.77 | 81.31 | 76.19 |
| L2-QK | 94.28 | 91.62 | 88.01 | 84.49 |
| One-pass logits | 95.64 | 74.70 | 86.16 | 82.01 |
| Two-pass logits | 96.12 | 74.10 | 85.93 | 81.30 |
On MATH, L2-QK achieves the highest BA among the evaluated methods, improving over one-pass logits by 16.92 percentage points. On HLE, L2-QK achieves the highest AUROC and BA, exceeding one-pass logits by 1.85 and 2.48 percentage points, respectively. For the camera-ready version, we will adapt the QK readout to Qwen 3.5 specific hybrid delta-net attention architecture.
Rebuttal 3/3
Q5: Can you evaluate the method on non-mathematical reasoning tasks?
A: We added two benchmarks. On LiveCodeBench (release_v6), a generated program is correct if it passes all released tests under the official checker. On ProofWriter (open-world setting, depth 5), the model generates a response ending in True, False, or Unknown. We check that conclusion against the published answer.
We evaluated Qwen3-8B and Qwen3-14B. For each model and benchmark, all methods scored the same 450 held-out responses. A separate set of 50 task-specific examples supplied the unlabeled reference for CF-QK and the 30/10/10 fitting, validation, and threshold-selection split for L2-QK. No test labels were used for fitting. CF-QK weights were frozen before evaluation.
Table 26. LiveCodeBench verification. Entries are AUROC / balanced accuracy (%). Bold marks the best value for each metric within a model.
| Method | Qwen3-8B | Qwen3-14B |
|---|---|---|
| CF-QK, one-pass | 81.06 / 73.61 | 75.58 / 71.01 |
| CF-QK, counterbalanced | 82.38 / 72.87 | 79.99 / 70.12 |
| L2-QK | 85.70 / 80.09 | 84.16 / 73.05 |
| Verdict logits, one-pass | 84.34 / 67.04 | 83.29 / 69.09 |
| Verdict logits, two-pass | 84.83 / 74.35 | 83.94 / 71.84 |
Table 27. ProofWriter verification. Entries are AUROC / balanced accuracy (%) on the same 450 test responses per model.
| Method | Qwen3-8B | Qwen3-14B |
|---|---|---|
| CF-QK, one-pass | 64.83 / 61.26 | 57.19 / 56.60 |
| CF-QK, counterbalanced | 57.97 / 54.37 | 58.57 / 55.87 |
| L2-QK | 76.14 / 68.98 | 60.69 / 58.58 |
| Verdict logits, one-pass | 39.97 / 49.75 | 59.16 / 50.30 |
| Verdict logits, two-pass | 46.96 / 50.07 | 59.51 / 50.33 |
Both QK methods use source examples from the task on which they are evaluated. These in-domain experiments show that QK scores carry information about correctness in code generation and deductive reasoning.
Q6: Are 50 examples sufficient for a readout over many attention heads?
A: In our experiments, 50 labeled source examples were sufficient to fit a useful L2-QK readout. We used 30 examples to select a pool of 128 heads and fit an L2-regularized classifier, 10 to select the regularization strength, and 10 to choose the decision threshold (§4.3). The underlying language model stayed frozen.
Repeated calibration. We repeated the full procedure on ten stratified source splits per model, averaging three search seeds within each split. Table 2 (§6.2) reports mean balanced accuracy across the eight model–dataset comparisons. Table 14 (Appendix C.5) reports the paired differences from verdict logits calibrated with the same label budget.
Label-budget scaling. For Qwen3-8B, we varied the source budget from 50 to 100, 200, and 400 labels while keeping the same 100 held-out MATH solutions. As the budget increased, mean balanced accuracy rose and the selected head pools overlapped more across splits (Appendix C.6, Figure 4).
Threshold sensitivity. We also held the original Qwen3-32B classifier fixed and resampled its ten threshold-calibration examples 1,000 times using stratified sampling. The resulting standard deviation in balanced accuracy was 7.30 percentage points on MATH and 5.77 on HLE. AUROC stayed constant because the underlying scores and their ranking were fixed.
Rebuttal 1/3
We thank the reviewer for the detailed feedback. We first address the questions about manuscript preparation and the conduct of the experiments, then explain the revisions and additional results. We have uploaded the revised manuscript to OpenReview. We have not changed the proposed method, the original experimental protocols, or any of the original main results. The revisions improve the exposition and add separate, supplementary experiments.
Q1: "What proportion of the manuscript was carefully reviewed by humans?"
A: We wrote the manuscript and carefully reviewed every part of it ourselves (100%), including the main text, methodology, experimental analyses, tables, figures, and appendices.
As documented in our AI Use Statement, generative AI tools assisted with editing parts of the text, identifying related literature, formatting references, and suggesting alternative titles. We checked the scientific content and made all final editorial decisions. We also rewrote and carefully checked ourselves the introduction, methodology, and experimental discussion in the updated manuscript.
Q2: "Were humans sufficiently involved in conducting the experiments?"
A: We designed, implemented, and ran the experiments ourselves. We made all methodological decisions, established the experimental protocols, and analyzed, validated, and interpreted the results. For example, we manually audited 50 randomly selected Qwen3-32B MATH correctness labels.
In conducting the experiments, language models were used only as experimental subjects and, where documented by the paper, as evaluation tools. We conducted all the research ourselves.
W1: Introduction and motivation.
A: Section 1 (pp. 1–2) now begins with the practical question: when a model generates a candidate solution without access to the reference answer, how should we assess whether to accept it or seek further verification? We then ask whether the frozen model contains correctness information not fully reflected in its output verdict. This connects earlier QK-based answer selection to our extension to complete generated solutions.
Before the contributions, we explain the verification pipeline: the verifier receives a problem, a candidate solution, and two explicit verdict statements; each attention head expresses a relative QK preference between them; CF-QK aggregates these preferences without correctness labels, while L2-QK learns a regularized readout from a small labeled set. We removed the standalone Section 1.1 and placed the contributions at the end of the introduction.
W2: Methodological design principles.
A: Section 4 (pp. 3–5) now opens with the actual verification prompt and highlighted query/key read positions. Section 4.1 explains the signed head-level margin before introducing its mathematical definition. Section 4.2 motivates the aggregation rule through a concrete failure mode: a head can agree across read positions yet predict the same verdict for nearly every solution. CF-QK therefore considers both within-solution agreement and variation across an unlabeled reference batch. Section 4.3 explains feature selection, L2 regularization, validation, and threshold selection under the 30/10/10 source-label split. Each mathematical component is now accompanied by its rationale.