- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies the relationship between the probability of a generated continuation and the correctness of its answer. It examines this relationship across prompts, within prompts, under decoding-hyperparameter changes, and across decoding methods. Accuracy gains from decoding, voting and self-distillation are heterogeneous, with MATH500 providing the clearest positive pattern. The authors use these observations to discuss when likelihood-based selection and self-improvement may be useful. My primary concern is that the study still provides insufficient insight into the conditions under which response likelihood is useful for selecting a correct answer to a particular query.
Critical strengths
- A useful, bounded comparison across levels of analysis. The MATH500 pattern persists across model families and at individual-score resolution, while within-prompt associations are weaker. Together with heterogeneous decoding, voting and self-distillation outcomes, this illustrates why aggregate confidence does not necessarily rank candidates reliably within a query.
Critical weaknesses
-
Unresolved protocols limit interpretation. The reported HumanEval prompt count does not reconcile with the official dataset, which contains 164 problems. Dataset configuration, unique problems, repeated generations and correctness rules need clarification. Nonempty-response exclusion counts and treatment of constant-label pools, whose rank correlations are undefined, are missing. The stated universal Spearman upper bound might also be incorrect.
-
Limited insight into when likelihood is useful. Previous literature has explored related ideas (Taubenfeld et al.). The within-prompt, length-normalization, voting and distillation analyses deserve credit. However, Figure 7 pools models and benchmarks with visible dataset clustering; the rank correlations in Figure 9 are not paired selection gains and depend partly on candidate-label composition. The observed outcomes do not establish an accuracy threshold for improvement or a causal explanation of voting differences. The measured gains and MATH500 pattern remain useful, but I find the conditional insight insufficient even if reporting issues are corrected.
Questions for authors
-
Within-query answer selection. How are constant-label pools handled, and how many are excluded or assigned a value? What is the paired gain from the highest-probability candidate over the pool's mean correctness—the expected accuracy of random selection—within fixed model–benchmark settings? What do prompt-level uncertainty and available difficulty or prompt-success strata show?
-
Dataset, scoring and voting protocols. What dataset configurations, unique prompt and generation counts, correctness rules, and original/retained nonempty-response counts were used? If exclusions are material, do accuracy comparisons change when empty responses count as failures? Are voting weights raw probabilities, length-normalized probabilities or another transformation? How are extracted answers grouped and ties resolved?
4 comments
Rebuttal
We thank the reviewer for their thorough review and for highlighting the paper as “useful, bounded comparison across levels of analysis” and liking the “heterogeneous decoding, voting and self-distillation outcomes”.
Protocols
We thank the reviewer for highlighting these points. We add the following table to the appendix D.4
| Dataset | Source / config / split | Prompts | Correctness |
|---|---|---|---|
| MATH500 | HuggingFaceH4/MATH-500, test | 500 / 500 | MathVerify equivalence of the final \boxed{} answer |
| GPQA | Idavidrein/gpqa, gpqa_main, train | 445 / 448 | extracted letter |
| MMLU | cais/mmlu, all, test, first 500 | 500 | extracted letter |
| MedQA | GBaker/MedQA-USMLE-4-options-hf, test, first 500 | 500 | extracted letter |
| HumanEval | openai_humaneval, test | 164 / 164 | all unit tests pass |
| IFEval | google/IFEval, train, first 500 | 500 / 541 | strict prompt-level accuracy |
Additionally, we thank the reviewer for finding the subtle typos and missing bits in the main text.
- For HumanEval we use 164 problems
- For MMLU we use MMLU (4 options)
- Empty responses are counted as wrong
- The Spearman bound is off, it should read
- Voting weights in the paper are raw sequence probabilities.
- Constant-label pools are excluded from the corresponding analysis
Within-query answer selection
We thank the reviewer for raising this point. We compute the gain of the most probable of 32 LTS candidates over the pool's mean correctness. It is positive for 7 of 14 models on MATH500 (mean +1.7 points), 3 on MedQA (+1.4), at most 1 on the other benchmarks (means −1.8 to −0.4). For “prompt-success strata” the paired gain stays within -1.4 and +1.2 points in every stratum while correlation rises. We measure prompt-level uncertainty by the agreement of the 32 samples and get the same picture. In no stratum is the most probable response significantly better than a random response.
Usefulness of likelihood
We thank the reviewer for highlighting the work by Taubenfeld et al. (2025) (Appendix A). It computes a similar quantity as the within-prompt correlation. However, our scope differs. While we study sequence probability as the quantity that many decoding methods use, additionally we show correlations (and no correlations) at various other levels. With dataset fixed effects, the relation holds for posttrained models but is mainly between datasets for base models. We restate Finding 4 accordingly.
We hope that the revised paper alongside our comments address the reviewer's concerns, and we would be grateful if the reviewer would reconsider their score.
Thank you for the rebuttal and for adding the paired comparison. The rebuttal arrived late in the discussion period, which left me limited time to assess the new analysis in depth and discuss it further with the authors. The paired comparison addresses my question, but the aggregate results leave uncertainty about how much sequence probability helps with within-prompt answer selection when task accuracy is high. Based on the evidence available, I am inclined to maintain my original rating of 2.
We thank the reviewer for following up with our rebuttal. We would also like to sincerely apologize for the rebuttal arriving late.
Regarding the remaining question, we can group the paired comparison by accuracy as follows.
| Accuracy | Pairs | Mean gain |
|---|---|---|
| < 40% | 32 | −1.2 pts |
| 40–60% | 20 | −1.3 pts |
| 60–75% | 19 | +2.0 pts |
| ≥ 75% | 13 | +0.6 pts |
Selecting a response solely based on sequence probability, only helps when accuracy is high and then modestly. It is never significantly worse and the effect is also not limited to MATH500.
To make this point again, in the paper, we are trying to faithfully measure correlations between sequence probability and correctness to strengthen the understanding of practitioners when choosing models, decoding methods, and datasets. We do not have the goal of providing improved methods for certain use cases.
We would like to thank the reviewer again for their reponse.
As no rebuttal provided, I'd maintain my original score.