- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes a unified framework, Omni-Truth, to mitigate hallucinations in both open-domain and closed-domain scenarios, referring to free-generation and context-based generation, respectively. The framework has three stages. First, it starts with SFT on reflection-then-correction responses. Then it applies GRPO to obtain a closed-domain specialist and a Cascade policy. Finally, it uses MOPD to complete task-specific policy consolidation. The authors empirically evaluate Omni-Truth on several benchmarks with Qwen3-8B model and compare against baselines. Experimental results along with ablation studies validate the effectiveness of Omni-Truth in improving both open-domain factuality and closed-domain faithfulness.
Critical strengths
A useful empirical improvement in contextual faithfulness and factuality. The paper addresses a practically important challenge for models that must both follow supplied evidence and answer from parametric knowledge. Relative to the Closed-to-Open Cascade, Omni-Truth improves FACTS Grounding while also improving MultiHopRAG and the open-domain average. These results provide evidence that consolidation can partially recover source grounding weakened by sequential training while preserving the benefits of that training. This demonstrated improvement in the balance between the two objectives is the main empirical strength supporting acceptance in my assessment.
Critical weaknesses
-
Limited novelty and insufficient support for the main design choices. The Omni-Truth framework follows a pipeline similar to that of MOPD [1]. Its main changes include Cascade student initialization and task-specific use of the Closed-only and Cascade teachers and . The initialization ablation supports starting from the Cascade policy. However, the evidence for the chosen teacher pair and task assignment is less clear. The authors provide a plausible explanation based on the teachers’ benchmark scores, but the current comparisons change several parts of the configuration at once. They therefore do not clearly show whether the gains come from the proposed teacher selection and assignment. Comparisons with alternative teachers or assignments under otherwise matched conditions would provide stronger support. Moreover, the paper does not isolate whether reflection-specific supervision improves the final model over comparable SFT without reflection. These gaps leave the methodological contribution beyond adapting MOPD insufficiently established.
-
Limited evidence that the selected configuration generalizes. All controlled training experiments use Qwen3-8B. The final method improves the Macro score by 0.74 percentage points over both Cascade and Standard MOPD, and by 0.35 points over Naive Cascade MOPD. Some individual gains are larger, but they come with lower scores on other benchmarks. The chosen teacher pair, although having strengths in this setting, may change with the backbone, which could also change the preferred initialization and teacher group. The paper does not test whether the proposed configuration remains effective under different settings. Thus, it remains unclear whether Cascade initialization and the chosen teacher pair provide a consistent advantage across models. Given the marginal performance gains, the evidence from a single backbone is insufficient to establish the broad applicability of the proposed framework.
[1] Ma, Wenhan, et al. "Mopd: Multi-teacher on-policy distillation for capability integration in llm post-training." arXiv preprint arXiv:2606.30406 (2026).
Questions for authors
Based on the two weaknesses, I have the following questions.
-
Contribution of reflection SFT. What specific benefit does reflection-and-correction supervision provide to the final model? Beyond the behavioral analysis in Appendix E.2, is there evidence that it improves final performance compared with otherwise comparable SFT without reflection?
-
Contribution beyond applying MOPD. Applying an existing method to a new setting can be valuable when it yields new insights. What does Omni-Truth establish about integrating closed-domain faithfulness and open-domain factuality beyond showing that MOPD is useful in this setting? In particular, what insight motivates the proposed teacher construction and task assignment, and which comparisons substantiate it? My concern is whether these adaptations provide a contribution beyond a task-specific configuration of MOPD. Clarifying this distinction would materially affect my assessment of the paper’s contribution.
-
Evidence beyond Qwen3-8B. Do you have results on another backbone or model scale showing that the proposed configuration improves over Cascade and Standard MOPD? Such evidence would help determine whether the observed advantage extends beyond the particular teacher strengths found on Qwen3-8B.
9 comments
Response to Reviewer dtRu (2/3)
W2.
Limited evidence that the selected configuration generalizes. All controlled training experiments use Qwen3-8B. The final method improves the Macro score by 0.74 percentage points over both Cascade and Standard MOPD, and by 0.35 points over Naive Cascade MOPD. Some individual gains are larger, but they come with lower scores on other benchmarks. The chosen teacher pair, although having strengths in this setting, may change with the backbone, which could also change the preferred initialization and teacher group. The paper does not test whether the proposed configuration remains effective under different settings. Thus, it remains unclear whether Cascade initialization and the chosen teacher pair provide a consistent advantage across models. Given the marginal performance gains, the evidence from a single backbone is insufficient to establish the broad applicability of the proposed framework.
We replicated the full comparison on Qwen3-4B, retraining all baselines with the same data and evaluation:
| Qwen3-4B | FACTS | HHEM | MultiHop | CRAG | WebQA | C-SQA | Close avg | Open avg | Macro |
|---|---|---|---|---|---|---|---|---|---|
| Closed-only RL | 80.62 | 97.95 | 74.56 | 31.49 | 63.30 | 29.14 | 84.38 | 41.31 | 62.84 |
| Open-only RL | 45.74 | 93.50 | 71.43 | 33.50 | 67.51 | 30.66 | 70.22 | 43.89 | 57.06 |
| Combined RL | 80.19 | 97.83 | 73.36 | 30.72 | 64.84 | 29.59 | 83.79 | 41.72 | 62.76 |
| Standard MOPD | 80.00 | 98.64 | 75.38 | 33.51 | 66.15 | 30.19 | 84.67 | 43.29 | 63.98 |
| Cascade (C→O) | 77.91 | 98.11 | 78.16 | 33.24 | 66.96 | 30.26 | 84.73 | 43.49 | 64.11 |
| Reverse Cascade (O→C) | 78.64 | 97.99 | 71.83 | 34.29 | 68.21 | 32.04 | 82.82 | 44.85 | 63.83 |
| OMNI-TRUTH | 78.22 | 98.48 | 78.72 | 34.40 | 66.87 | 30.34 | 85.14 | 43.87 | 64.50 |
The configuration transfers:
- The trade-off reproduces. The Cascade leads standard MOPD on MultiHopRAG (78.16 vs. 75.38) but trails it on FACTS Grounding (77.91 vs. 80.00).
- The limitation of standard MOPD lies in its teachers. It recovers its teachers almost fully (100.3% of its closed-domain teacher's average and 98.6% of its open-domain teacher's), but neither teacher has the Cascade's multi-document QA ability.
- OMNI-TRUTH keeps its advantage. It has the highest Macro among dual-domain methods (64.50, vs. 64.11 for the Cascade and 63.98 for standard MOPD) and is the only one above 78 on both FACTS Grounding and MultiHopRAG.
At 8B, the matched ablations in W1 isolate the teacher assignment, and the MultiHopRAG gain over standard MOPD is significant (sign test over 2,548 questions, ).
The margin over standard MOPD is concentrated by design. Standard MOPD here is the first merge of our own pipeline, built from our Closed-only and Open-only policies; since a distilled ability is largely bounded by its teacher, OMNI-TRUTH can only improve where those teachers fall short, and its gains lie exactly there:
- MultiHopRAG: 80.16 vs. 75.34 for standard MOPD (significant, above).
- FACTS Grounding: 73.13 vs. 70.30 for the Cascade it starts from. Its lower FACTS Grounding than standard MOPD (73.13 vs. 75.61; HHEM is within 0.16) is the cost of keeping the Cascade's multi-document QA, and OMNI-TRUTH recovers more than half of that gap (+2.83 of 5.31 points).
- CRAG: above standard MOPD in each of the three training runs (40.05–40.93 vs. 36.65–39.93; table below). Standard MOPD's behavior depends on the run, from answering almost every question (1.3% not attempted, 59.0% wrong) to declining 19.2% of questions by citing missing input; OMNI-TRUTH cites missing input in at most 6.6%.
- Open-domain average: 51.34, the highest among all Qwen3-8B methods in Table 1, including Open-only RL (50.21) and TruthRL (50.87).
| CRAG, Qwen3-8B | Score | Correct (%) | Wrong (%) | Not attempted (%) | Cites missing input (%) |
|---|---|---|---|---|---|
| Standard MOPD, run 1 | 39.93 | 39.7 | 59.0 | 1.3 | 0.0 |
| Standard MOPD, run 2 | 39.40 | 36.8 | 50.0 | 13.2 | 4.6 |
| Standard MOPD, run 3 | 36.65 | 31.5 | 40.5 | 27.9 | 19.2 |
| OMNI-TRUTH, run 1 | 40.05 | 39.1 | 56.0 | 4.9 | 2.2 |
| OMNI-TRUTH, run 2 | 40.11 | 38.5 | 53.6 | 7.9 | 2.5 |
| OMNI-TRUTH, run 3 | 40.93 | 37.1 | 44.3 | 18.6 | 6.6 |
The Macro margin is small because HHEM is saturated (97.8–98.5 for all dual-domain methods) and the open-domain benchmarks are bounded by the base model's parametric knowledge, so most benchmarks barely separate the methods. Against Naive Cascade MOPD (+0.35 Macro), OMNI-TRUTH gains 4.11 points on MultiHopRAG; that comparison changes initialization and teacher routing at once, which the matched ablations in W1 separate.
Response to Reviewer dtRu (3/3)
Q1.
Contribution of reflection SFT. What specific benefit does reflection-and-correction supervision provide to the final model? Beyond the behavioral analysis in Appendix E.2, is there evidence that it improves final performance compared with otherwise comparable SFT without reflection?
Yes (W1). At both scales, reflection SFT gives higher FACTS Grounding and HHEM and higher Macro than SFT without reflection. It teaches the model to verify and revise its answer against the input, the behavior that reduces closed-domain hallucination.
Q2.
Contribution beyond applying MOPD. Applying an existing method to a new setting can be valuable when it yields new insights. What does Omni-Truth establish about integrating closed-domain faithfulness and open-domain factuality beyond showing that MOPD is useful in this setting? In particular, what insight motivates the proposed teacher construction and task assignment, and which comparisons substantiate it? My concern is whether these adaptations provide a contribution beyond a task-specific configuration of MOPD. Clarifying this distinction would materially affect my assessment of the paper's contribution.
The study establishes three points beyond showing that MOPD is useful:
- Closed- and open-domain RL conflict because each single-domain policy carries its evidence rule into the other regime (the Closed-only policy declines 14.5% of CRAG questions by citing missing input; the Open-only policy reaches only 41.59 on FACTS Grounding). Standard MOPD over the two single-domain teachers resolves this conflict.
- This merge is not sufficient. MultiHopRAG, QA over supplied documents, gains from sequential closed-to-open RL (79.43 for the Cascade vs. 75.34 for standard MOPD), an ability neither single-domain teacher has, while the Cascade loses grounding (FACTS Grounding 70.30 vs. 75.61).
- The second merge must target both data and teachers. Using the Cascade as the student carries its open-domain ability, so this stage needs only closed-domain data. Each closed-domain task is assigned the teacher that holds the required ability: QA from the Cascade, summarization from the Closed-only policy.
The matched ablations in W1 substantiate this assignment: every alternative lowers Macro (by 0.44–1.46 points); QA distilled from the Closed-only teacher loses 4.6–5.1 points on MultiHopRAG and 1.3–4.1 on CRAG, and summarization distilled from the Cascade instead of the Closed-only policy loses 1.26 points on FACTS Grounding. The resulting model improves where each merge is aimed: MultiHopRAG 80.16 vs. 75.34 for standard MOPD, FACTS Grounding 73.13 vs. 70.30 for the Cascade, and CRAG above standard MOPD in every training run (W2). The pattern reproduces at 4B (W2). We will reframe Sections 1 and 4 accordingly.
Q3.
Evidence beyond Qwen3-8B. Do you have results on another backbone or model scale showing that the proposed configuration improves over Cascade and Standard MOPD? Such evidence would help determine whether the observed advantage extends beyond the particular teacher strengths found on Qwen3-8B.
Yes, on Qwen3-4B; see W2.
References
- [1] Ma, W., Wei, J., Zhao, L., et al. MOPD: Multi-teacher on-policy distillation for capability integration in LLM post-training. arXiv:2606.30406, 2026.
Response to Reviewer dtRu (1/3)
W1.
Teacher pair and task assignment under matched conditions.
Starting from the same Cascade checkpoint, with the same data and training budget, we varied only the teacher assigned to each task (Qwen3-8B):
Every alternative assignment lowers Macro, by 0.44–1.46 points. Whenever QA is not distilled from the Cascade, MultiHopRAG drops by 4.6–5.1 points and CRAG by 1.3–4.1, because the Closed-only teacher spreads over-abstention to QA (the Closed-only policy declines 26.3% of MultiHopRAG questions by citing missing input, vs. 18.5% for the Cascade). Distilling summarization from the Closed-only teacher instead of the Cascade adds 1.26 points on FACTS Grounding. QA must therefore come from the Cascade, and summarization from the Closed-only policy.
Reflection SFT vs. SFT without reflection.
OMNI-TRUTH uses reflection SFT as the shared starting point for both regimes. To test whether the reflection step matters, we sampled SFT data in the same format as the reflection SFT data but without the reflection suffix, and trained with the same SFT configuration, at both scales.
We repeated the comparison on Qwen3-4B with the same data pipeline, SFT recipe, and evaluation:
Reflection gives higher faithfulness at both scales: FACTS Grounding and HHEM are higher in every evaluation run, and Macro is higher as well. Reflection SFT teaches the model to check and revise its response against the input before answering: with reflection, most thinking traces on FACTS and HHEM contain an explicit verification step and a review step, while far fewer do without it (table below). These are the patterns that reduce closed-domain hallucination, and teaching them is the purpose of the SFT stage. The no-reflection model's advantages are limited and inconsistent. On MultiHopRAG it is ahead at 8B but behind at 4B. On CRAG it is about 3 points higher at both scales, but it shows no meaningful advantage on WebQA or Chinese SimpleQA. We therefore use reflection SFT.