- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes GAUGE, a verifier that measures model responses to typed prompt transformations with known answer mappings. It learns a latent metric, combines representational drift with answer agreement, and calibrates score thresholds using split conformal calibration. Supervised variants fit robustness predictors, while distilled variants score the candidate's own activations without extra generation. Experiments compare verifiers, diagnose prompt-level reliability, and use GAUGE to select self-training data. The reported robustness largely concerns repeated policy behavior on a prompt rather than the validity of a specific reasoning trajectory.
Critical strengths
-
The paper includes extensive comparisons and informative controls, including unedited resampling, within-prompt evaluation, and matched feature ablations. These clarify what the measurements actually capture.
-
The distilled predictor offers a modest but supported benefit without extra generation: hidden states add about 0.021 AUROC over confidence and length. This is a useful observation within the evaluated settings.
Critical weaknesses
-
The central verification story exceeds the demonstrated scope. The primary label mostly measures prompt-level reliability, and ranking correct trajectories within a prompt is near chance (AUROC 0.516). Unedited resampling reproduces 83% of the measured robustness gap, so most of that gap cannot be attributed specifically to sensitivity to edits or brittle shortcuts. The conformal result controls score coverage, not correctness or robustness among accepted candidates. These results provide limited support for verifying sound reasoning trajectories.
-
The added complexity has insufficient demonstrated payoff. With matched supervision and tuning, predictors with and without latent features both reach 0.783 AUROC; the latent increment is 0.000. The distilled benefit is real but small. Self-training gains over outcome filtering are only 0.8-1.0 percentage points and are not significant after multiple-comparison correction. Probe-based scoring also needs about 7.6 extra rollouts per candidate. The evidence does not establish enough value beyond simpler consistency-based prediction to justify the full procedure.
Questions for authors
-
Can GAUGE reliably distinguish better reasoning trajectories within the same prompt under candidate-linked labels and matched unedited-continuation controls? What evidence supports the shortcut-verification interpretation beyond general sampling instability?
-
What practical benefit requires the learned latent metric when a matched predictor using probe answers, confidence, and length performs equally well? Please clarify the contribution beyond counterfactual consistency testing and its distillation.
-
Do the self-training gains remain with the probe-free predictor, under a matched total-compute budget? More repeated runs and broader agent experiments would help establish whether the modest gains are reliable and practically useful.
2 comments
W2 / Q2. What requires the latent construction, and is it worth the probes?
We agree with the matched ablation: with labels, predictors with and without the latent features both reach 0.783. The revision says so. What the construction contributes is the following:
- Typed interventions make a better target and teacher than plain consistency. GAUGE-LR+ exceeds paraphrase agreement by +0.073 [+0.043, +0.102] (21/23). Adding answer-changing and diagnostic edits to meaning-preserving ones raises the label-free score from 0.695 to 0.744.
- The robustness signal is readable from the candidate's own hidden states, whatever the teacher. Distilling into those hidden states adds +0.021 to +0.025 AUROC over confidence and length, whether the teacher is GAUGE-LR+, the matched predictor without latent features, or raw probe agreement (Table 35).
- That readout removes the probe cost. Ranked together with the self-consistency of the already sampled pool (an unweighted rank sum), it reaches 0.782 conditional AUROC with no probe generated, matching the probe-based predictor (0.783).
- It beats pool self-consistency by +0.056 [+0.026, +0.087] (19/23).
- At best-of-8 it submits a strictly robust answer 69.7% of the time, against 68.7% for self-consistency (+1.0 pp [+0.1, +2.0]) and 70.0% for GAUGE-LR+.
The 7.6 probe rollouts per candidate are therefore an offline cost of building the teacher, not a deployment cost.
Reference-free in practice. Only the misleading-answer decoy ever read the reference. Rebuilding it from each candidate's own answer, and regenerating the 684 affected rollouts, moves conditional AUROC by ≤ 0.0001 and unconditional AUROC by ≤ 0.0002 (Appendix R).
Q3. Self-training with the probe-free predictor, and its compute
We ran it (Qwen3-4B; the same 1,500-prompt mixed pool spanning ALFWorld, τ-bench, math, code, tool calls and ARC; 3 seeds × 3 rounds of LoRA rejection fine-tuning). All arms use the same 4 samples per prompt and keep one gold-correct candidate per eligible prompt, so sampling, data and training are matched; we measured total compute rather than equalizing it. The probe-free head was distilled once, from typed-probe agreement, and frozen.
| Selector (3 seeds) | Extra generations at selection | GPU-h / seed | Paired Δ vs. outcome (Table 1 test) |
|---|---|---|---|
| Outcome-RFT | 0 | 3.5 | — |
| Probe-agreement-RFT | 7.6 / candidate | 17.8 | +0.2 pp [−2.6, +3.0] |
| GAUGE-RFT, probe-free | 0 | 4.4 | +0.4 pp [−2.2, +3.0] |
GPU-hours cover sampling, scoring, selection and training on one GPU; the probe-free arm includes its one-off head fit (2.1 h), spread over the three seeds. Per-suite results, including ALFWorld and τ-bench, are in Table 37.
The probe-free selector matches the probe-based one at a quarter of the compute: +0.4 vs. +0.2 pp over outcome filtering, at 4.4 instead of 17.8 GPU-h per seed, and only 1.26× the cost of outcome filtering. As in Table 1, the self-training effect of either selector is small and not resolved at three seeds, and we present it that way. The reason is leverage: on the base-policy pool, typed-probe agreement differs among the correct candidates of only 21% of eligible prompts (232 of 1,130), so any within-prompt selector can change the kept candidate's robustness on few prompts. Where the score acts directly on the output, its gains are resolved: at best-of-8 (+1.0 pp over self-consistency, zero extra generations) and in conformal acceptance (1.5×).
We thank the reviewer. These questions sharpened the paper: GAUGE estimates counterfactual reliability from a trajectory's representation, bounds the fragile share of what it accepts, and needs no probes at deployment.
We thank the reviewer for a thorough and technically precise review. Two of the reviewer's points led to results that change the picture:
Section, table and appendix numbers are unchanged from the submission; the three new tables are Tables 35–37 in a new Appendix X.
Changes in the revision
W1 / Q1. Within-prompt discrimination, shortcuts, and what is accepted
Within a prompt. We agree that the primary label is mostly prompt-level. Only 24% of prompts contain correct candidates whose labels differ, and GAUGE-LR+ ranks within a prompt at 0.516.
We also tested a candidate-linked label: fix the first half of a candidate's reasoning and test its continuations (17 configurations, 654 informative prompts).
Within-prompt discrimination is therefore real, and it comes from prefix stability. The revision describes GAUGE as an estimate of counterfactual reliability read from a trajectory, not as a check of a specific shortcut. That is the quantity data curation and output acceptance act on.
Edits beyond resampling. Edits are a distinct failure mode. Among initially correct candidates, 18.5% fail held-out edits, against 15.3% under an equal number of unedited resamples: +3.2 pp [+2.2, +4.1], positive in 19/23 configurations, with a median ratio of 1.6×. The abstract, §1 and §4.2 now report this decomposition.
A guarantee on what is accepted. We added conformal selection (Jin and Candès, 2023; §3.5, Appendix A.8, Table 36). Unlike the original score-coverage guarantee, conformal selection controls the expected proportion of fragile trajectories among accepted outputs. Under exchangeability, it guarantees
E[max(1,R)V]≤q
where V is the number of fragile accepted trajectories, R is the total number of accepted trajectories, and q is the target false discovery rate.
To account for dependence among candidates sharing a prompt, calibration and evaluation each use one randomly selected candidate per prompt group. We average results over 100 representative draws per configuration, across 23 configurations.
GAUGE-LR+ accepts +0.168 [+0.082, +0.265] more of the robust trajectories than self-consistency (16/23), i.e. 1.5× as many. The label-free score adds +0.125 [+0.057, +0.204], and the zero-generation verifier +0.084 [+0.026, +0.151]. Every realized share is within two standard errors of its target. The advantage is at strict tolerances; at q = 0.10 the scores tie (Table 36).