- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper predicts the correctness of an LLM answer using features extracted at the final input-token position before generation. The estimator uses three mechanistic descriptors, selected attention-sink values, cosine alignment between attention and feed-forward contributions, and two normalized residual-trajectory statistics. A small branch-attentive probe is then trained based on these three descriptors. Experiments show the effectiveness of the proposed estimator.
Critical strengths
- The paper is well-written and easy to follow.
- The proposed descriptors are reasonably easy to implement for models with internal access.
Critical weaknesses
- There is no analysis of the statistical properties of the proposed estimator. The current theoretical results establish elementary properties that motivate the feature design, but they do not show the proposed estimator's reliability.
- The mechanistic justification for the three descriptors is underdeveloped. The current ablations support their predictive usefulness and complementarity, but do not explain why these particular statistics should reflect answer correctness.
Questions for authors
- What is the purpose of the four elementary properties in Sec. 4.5? I hope the authors explain more about the insights from this theoretical analysis and provide more results on the estimator’s statistical properties.
- Could the authors design explicit mechanistic hypotheses for each descriptor and provide controlled experiments with statistical tests to evaluate them?
Thank you for the rebuttal and the updated manuscript. The added 7B/8B linear probe results, seed std numbers, and Q5 clarifications resolve the setup questions, and I understand the compute limits around 70B/72B inference. Still, four main concerns remain unresolved, most of which need little to no extra LLM forward passes:
On W1/Q1, P(IK) and the MC answer-option probability baseline are still missing on 7B/8B. Since candidate answer logits are already computed for argmax on MC tasks, reporting the option-probability baseline on Qwen2.5-7B and Llama-3.1-8B costs virtually no extra forward passes and is needed to isolate what the internal descriptors add.
On W2/Q3, validation-split temperature scaling only fits one scalar on existing prediction scores with negligible compute, and skipping it leaves calibration uncalibrated. In Table 1, 4 out of 5 baselines, namely Self-Cons., SE, EAGLE, and SEP, are either training-free or trained on semantic entropy rather than 0/1 correctness labels, as confirmed for SEP with 61.97 ECE. Comparing their raw ECE against an in-distribution BCE-trained probe overstates the calibration gain, while against the only same-target baseline I^2, the proposed method's AUROC gains are modest at 0.74 to 2.74 on average and lose on 3/20 settings.
Regarding Q2 and Appendix H.3, the new permutation check only tests concatenated 28-layer full update-direction vectors on MMLU within coarse median-length strata, rather than the proposed 2-scalar descriptor r(x) or the trained probe itself, and it skips GSM8K where r(x) alone hits 70.01 AUROC.
For W3/Q4, cross-domain transfer results are still limited to Qwen2.5-7B, where GSM8K->MMLU drops to 0.41 and most gains come from the three MC datasets. Testing already-trained probes on saved Llama-3.1-8B features requires no extra LLM inference.
Combined with the limitation acknowledged with Reviewer zhHM that the current setting only covers deterministic pre-generation prediction rather than stochastic decoding, I will keep my rating at 2 (Weak rejection) for now, and would be glad to reconsider if these 7B/8B baselines and calibrated comparisons are added.