- Rating
- 2
- Confidence
- 3
- Informativeness
- 3(+2)
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The work studies how source credibility labels affect fact-checking models before and after RL training. TrustSwap changes these labels while keeping evidence texts and source names fixed, and measures verdicts, confidence, and search flags separately. The results show that labels alone can change verdicts, and GRPO can amplify this effect at 8B. The authors propose trust-swap augmentation (TSA), which trains on original and swapped evidence with the same gold verdict. At 4B, TSA reduces flips in four of six settings, mainly through fewer changes to or from NEI. No significant reduction is detected at 8B.
Critical strengths
-
TrustSwap provides a controlled test showing that source labels alone can change fact-checking verdicts. Evaluating verdicts, confidence, and search flags separately helps distinguish unwanted verdict changes from intended responses to source credibility.
-
TSA is simple to incorporate into GRPO and leaves the base reward unchanged. At 4B, it reduces verdict flips in several settings while retaining accuracy and directional confidence and search-flag responses.
Critical weaknesses
-
TSA's benefit is narrow. In the main 4B setting, almost all of the 1.12 percentage-point reduction comes from fewer abstention flips, with no measurable reduction in SUPPORTS–REFUTES reversals. Since abstention under low trust can be appropriate in some deployments, the practical benefit depends on the stricter contract. The principled prompt's advice to avoid definitive verdicts under low trust further complicates the interpretation of NEI flips.
-
Evidence for broader effectiveness is unclear. TSA improves on unseen label removal at 4B, but the downshift gain is not significant, and no 8B setting shows a significant reduction. Training uses only 311 claims and 25 steps, with three TSA seeds at 4B; different learning rates also make it difficult to separate scale from optimization effects. An original-only control is still needed to isolate the benefit of swapping labels from extra sampling.
Questions for authors
-
To distinguish label-driven shortcuts from abstention encouraged by the prompt, could you test a version of the principled prompt that retains verdict invariance but removes the advice to avoid definitive verdicts under low trust?
-
To isolate the contribution of label swapping from extra sampling, could you add a compute-matched control using two separate groups of G=8 rollouts from the original evidence, with the same reward, within-group advantage normalization, and optimization schedule as TSA?
6 comments
Thank the authors for the response, it partially addresses my concerns, but two main concerns remain.
-
Reducing transitions from correct verdicts to NEI does not prove that the abstentions are wrong, especially with low-trust evidence. To better assess the overall impact, it would help to include changes in transitions from incorrect verdicts to NEI and to analyze the trade off between accuracy and abstention.
-
The new results with no-advice prompt show that reversals persist, and there is no evidence that TSA helps mitigate the reversals. Specifically, after GRPO, the reversal rate decreases from 2.4% to 2.0%, while the total flips increase comes from changes in abstention.
We thank the reviewer for the follow-up. We address both points below with additional analyses of the existing model outputs.
1. Are abstentions under low-trust labels useful?
If abstaining on low-trust evidence is a sensible policy, these abstentions should mostly remove wrong verdicts and make the remaining answers more accurate. We tested this on the pairs where the swap lowers the labels from high to low trust and leaves the evidence text unchanged (AVeriTeC, neutral prompt, confident pairs).
| Model | Method | Correct -> NEI | Wrong -> NEI | Accuracy change (pp) | Selective accuracy, high -> low trust (%) | Confidence-based abstention, same coverage (%) |
|---|---|---|---|---|---|---|
| Qwen3-4B | GRPO baseline | 4.0 | 2.7 | −3.9 | 74.5 -> 74.5 | 76.7 |
| TSA | 3.5 | 2.3 | −3.9 | 74.5 -> 73.9 | 76.6 | |
| Qwen3-8B, standard GRPO | GRPO baseline | 5.9 | 6.3 | −5.0 | 71.9 -> 73.0 | 75.5 |
| Compute-matched control | 7.5 | 7.1 | −6.7 | 71.3 -> 72.3 | 75.2 | |
| TSA | 5.2 | 5.5 | −5.3 | 70.3 -> 70.2 | 73.7 |
Transitions are per 100 pairs. Selective accuracy is the accuracy on non-NEI answers; the last column shows it when the model instead abstains on the same number of its least-confident answers.
The data do not support this policy. About half or more of the withdrawn verdicts were correct (60% at 4B, 48% at 8B). Lowering the labels costs the baselines 3.9 to 5.0 pp of accuracy, while selective accuracy improves by at most about 1 pp. At the same coverage, confidence-based abstention gives 2.2 to 3.5 pp higher selective accuracy for every model in the table, so abstaining because of the labels is a weaker selective-prediction rule than the model's own confidence.
TSA reduces both transitions, which is the intended effect when the evidence should decide the verdict. At 8B, compared with the compute-matched control, it withdraws 2.3 fewer correct and 1.5 fewer wrong verdicts per 100 pairs and loses 1.4 pp less accuracy (all significant); at 4B, the accuracy cost is unchanged. A system that should be cautious with low-trust evidence can still use the confidence and search outputs, which TSA keeps responsive to the labels. Details are in Appendix M.
2. Reversals
This matches the scope stated in the paper: TSA's gains "come from fewer abstention changes rather than fewer reversals" (Sec. 1), and reversals remain the main open problem (Sec. 7, Sec. 8). We target abstention flips because they are most label-driven flips (78% for the 4B baseline, Sec. 4) and the part that RL fine-tuning amplifies. The no-advice results show the same pattern: after training, abstention flips increase while reversals do not (2.4% -> 2.0%). TSA reduces this amplified part and keeps reversals at the baseline level, with no significant difference in any of the six 4B settings and in eight of the nine 8B settings (Appendix K). Reversals already exist in untrained models and no method in our study reduces them; TrustSwap reports them separately so that future work can target them directly.
We hope this answer can solve the reviewer's remaining concerns.
We thank the reviewer for the two concrete experimental suggestions, both of which we have run as specified.
Q1. Principled prompt without the advice to avoid definitive verdicts.
We retained the verdict-invariance rule and changed only the advice. The search rule now reads: "...set
needs_more_search: yes, and still give the verdict that the evidence content supports" (originally: "...rather than committing to a definitive verdict").Table R4. Qwen3-8B, AVeriTeC, paper's GRPO setup: flip rate / abstention flips / reversals (% of confident pairs; GRPO baseline = mean of 5 seeds).
The results confirm that the advice accounts for part of the abstention flips: removing it lowers the flip rate from 15.8% to 11.2% for the untrained model and from 22.2% to 16.5% after GRPO. However, the shortcut persists without the advice: the untrained model still changes 11.2% of confident verdicts (10.1% with the neutral prompt), and GRPO raises this to 16.5%. Reversals, which the advice cannot explain, remain at 2.0–2.4%. Moreover, our main setting uses the neutral prompt, which contains no such advice, so the main results do not depend on it. On Qwen3.5-4B, removing the advice has little effect on the untrained flip rate (5.9% → 5.4%). In the revision, we will add the no-advice prompt and qualify the §4 paragraph on stating the rule in the prompt.
Q2. Compute-matched original-only control.
We trained the control exactly as specified: two separate groups of G=8 rollouts on the original evidence, with the same reward, within-group advantage normalisation and optimisation schedule as TSA.
Under standard GRPO on Qwen3-8B, the control separates the two effects. Additional rollouts alone increase the main-setting flip rate over the baseline (+1.63 pp [+0.43, +2.93]), whereas TSA decreases it. TSA is 2.99 pp below the control [−4.47, −1.75] and lower in 7 of 9 settings, including both unseen perturbations; a paired bootstrap yields the same conclusion. Under this objective, the gain is therefore attributable to the swapped labels rather than to additional sampling. As in the comparison with the baseline, the reduction is in abstention flips rather than reversals.
Under the paper's GRPO setup, the two cannot be separated. At 8B, neither lowers the flip rate (TSA − control −0.42 pp [−2.14, +0.96]). On Qwen3.5-4B, which we used because Qwen3-4B was withdrawn from the training service and which loses 6–8 pp accuracy with our 4B hyperparameters, both lower it by similar amounts (TSA − control +0.62 pp [−0.97, +2.51]). In the revision, we will add the control to every table and state this dependence on the objective.
W1. The benefit is narrow.
The avoided abstention flips are nevertheless relevant: when the 4B baseline switches to NEI after a label change, the original verdict was correct in 58% of cases, and TSA reduces these cases (−0.51 pp [−0.96, −0.10]). Deployments that prefer to abstain under low trust can do so through the confidence and search outputs, which TSA preserves (see our response to Reviewer onKv, Q1).
W2. Broader effectiveness, seeds and learning rates.
Scale versus optimisation. The 4B learning rate made 8B training unstable, so the 8B learning rate was selected only on the baseline's accuracy and NEI rate, without reference to any TrustSwap metric (§5.1). With this learning rate, switching to standard GRPO makes TSA's effect detectable at 8B: −1.37 pp in the main setting [−2.83, −0.04], −1.62 pp on CONFACT with the neutral prompt, and reductions under both unseen perturbations, including the downshift (−1.48 pp [−2.46, −0.51]), which was not significant at 4B. This is consistent with the explanation in §6 that the 8B result reflects optimisation rather than scale alone, and the compute-matched control does not reproduce this gain (Q2).
Seeds. All new models are trained with 5 seeds. Additional 4B seeds could not be run because the training service withdrew the 4B model (§5).
Training size. We agree that 311 claims and 25 steps constitute a controlled study rather than a full-scale training run; longer training on more claims is discussed as future work (§7).
We hope that these results address the reviewer's concerns, and we would appreciate it if the reviewer would consider updating the score accordingly.