- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes H-MPO to reduce cross-modal hallucinations in omni-modal language models. It uses modality-guided decoding to construct four ranked responses, then applies a SimPO-based objective with asymmetric margins and token-level reweighting. Experiments on Qwen2.5-Omni-3B and 7B show improvements on hallucination-specific as well as genral benchmarks.
Critical strengths
- The pipeline requires neither manual preference annotation nor a stronger teacher model. This reduces the cost of constructing preference data and makes the approach applicable where reliable annotations or stronger models are unavailable.
- The method improves aggregate hallucination metrics at both model sizes, results also show gains in general audio-visual and audio understanding.
Critical weaknesses
- Limited training queries coverage. Training samples uses only audio-only or video-only description questions, which is not diverse and differ significantly with many downstream apllications. Although results on DailyOmni are encouraging, performance on questions requiring both modalities remains unclear, limiting evidence for broader audio-visual generalization. I would very much like to see the improvements on questions that require both audio and video input.
- Unverified supervision quality. Though the idea is intuively correct and is supported by some case studies, the intended four-level ordering is not independently validated, especially whether (y_1) is more accurate rather than merely more detailed than (y_2). Likewise, token probability differences measure modality sensitivity but do not establish factual grounding. These uncertainties affect the reliability of the training signals as well as better understanding of the method.
Questions for authors
- How does H-MPO perform on DailyOmni questions (or other benchmarks) requiring both audio and video? This would clarify whether suppressing irrelevant modalities also preserves the use of complementary evidence.
- Table 3 reports general-capability results only for 3B. Does the 7B model also preserve DailyOmni and MMAU performance? This is particularly relevant because 7B uses full fine-tuning, whereas 3B uses LoRA. Also, experiments on other model families (beyond Qwen) would improve soundness of this method.
- The preferred response is generated by the same backbone so it may still contain errors or omit important details. Would generating it with a stronger model, or grounding it with ASR transcripts and stronger visual captions, improve H-MPO?
6 comments
W2 & Q3: Self-Generated Preference Data vs. Stronger Teacher Data (7B 3B)
Thank you for proposing this insightful direction and perspective. Our Modality-Guided Decoding (MGD) and H-MPO framework is intentionally designed to be self-contained, constructing multi-level preference data entirely from the model itself without relying on stronger teacher models. Nevertheless, we shared the exact same intuition early in our exploration and conducted an ablation study on Qwen2.5-Omni-3B using preference data synthesized by a stronger Qwen2.5-Omni-7B model. As shown in the table below, using 7B-generated data not only lags far behind self-generated 3B data, but actually degrades performance below the untuned 3B baseline:
| Training Data Source | CMM V-L | CMM A-L | CMM V-A-L | AVHBench (A$\rightarrow$V) Acc | AVHBench (A$\rightarrow$V) F1 |
|---|---|---|---|---|---|
| Qwen2.5-Omni-3B (Baseline) | 91.00 | 85.50 | 91.75 | 77.78 | 73.31 |
| H-MPO (7B-Data 3B) | 88.00 | 85.75 | 87.50 | 72.90 | 63.84 |
| H-MPO (3B-Data 3B, Ours) | 91.25 | 86.50 | 93.00 | 82.08 | 79.22 |
This empirical finding strongly validates the core design philosophy of our self-synthesized pipeline: the essence of mitigating cross-modal hallucination is not injecting external new knowledge from a stronger teacher, but calibrating the model to suppress its own intrinsic cross-modal interference.
Thank you for the detailed response and additional experiments. The new results on joint audio-visual understanding, general capability preservation for the 7B model, and another model family address most of my concerns and are encouraging.
However, my second weakness regarding supervision quality remains insufficiently addressed. Particularly whether is more factually accurate rather than simply more detailed than . Likewise, the connection between token-level probability differences and factual grounding remains unverified.
Overall, I appreciate the additional evidence and remain positive about the paper. I will maintain my original rating, which already reflects a favorable assessment.
We appreciate the reviewer's recognition of our core strengths, specifically that our pipeline requires neither manual preference annotation nor a stronger teacher model, and that our method consistently improves hallucination metrics across model scales while yielding gains in general audio-visual and audio understanding.
W1 & Q1: Joint Audio-Visual Understanding Evaluation
Thank you for this constructive suggestion. As shown in the table below, H-MPO consistently improves performance on tasks requiring joint understanding, covering both 7B and an additional benchmark (AV-SpeakerBench, an audiovisual QA benchmark featuring speaker-aware questions and aligned clips with trimmed audio, visual, and audiovisual segments to probe fine-grained cross-modal reasoning). On DailyOmni (which evaluates complex daily scenarios requiring joint audio-visual comprehension), H-MPO consistently improves accuracy for both Qwen2.5-Omni-3B and Qwen2.5-Omni-7B. On AV-SpeakerBench, which strictly requires aligned audio-visual cross-modal reasoning rather than single-modality shortcuts, H-MPO further yields performance gains across both model scales. These results demonstrate that while effectively suppressing cross-modal hallucinations, our method successfully preserves and leverages complementary audio-visual evidence.
Q2: General Capability Preservation (7B Full Fine-Tuning) & Cross-Architecture Generalization
Thank you for raising these valuable suggestions regarding general capability preservation and cross-architecture validation: