PACD: Provenance-Aware Consensus Decoding for Mitigating Cross-Modal Hallucinations in Omnimodal Large Language Models
Organizations: Xi’an Jiaotong University · University of Toronto · Tsinghua University · Pengcheng Laboratory
Abstract
Omnimodal large language models (Omni-LLMs) integrate audio, video, and text for multimodal reasoning, yet remain vulnerable to cross-modal hallucinations, where one modality improperly influences predictions about another. Existing training-free decoding methods mitigate these errors through modality perturbation or relevance-based weighting. However, due to interference from irrelevant modality cues during fusion and difficulty detecting shared errors, these methods may suppress correct unimodal predictions and allow erroneous consensus to persist. To address these limitations, we propose Provenance-Aware Consensus Decoding (PACD), a training-free framework for mitigating cross-modal hallucinations. PACD comprises two complementary paths based on whether the branches reach consensus. For non-consensus cases, Relevance-Guided Candidate Arbitration identifies task-relevant unimodal evidence and selectively arbitrates between predictions using alternative candidates. For consensus cases, Provenance-Based Consensus Recovery leverages the outranking principle to evaluate the consistency and strength of layer-wise modality evidence for alternative answers, selectively resolving erroneous consensus under confidence constraints. Extensive experiments on four Omni-LLMs and five benchmarks across two tasks demonstrate the superiority of PACD. Compared to existing methods, PACD achieves up to 27.6% relative improvement over standard decoding across CMM, AVHBench, and SVHalluc for cross-modal hallucination mitigation, and an average relative improvement of 7.7% over best baseline across OmniVideoBench and FutureOmni for general audio-visual reasoning.
Figures & tables
| Method | CMM | AVHBench | SVHalluc | ||||||
| Visual Dom. | Audio Dom. | Overall Acc. | Video-Driven Audio Hall. | Audio-Driven Video Hall. | Overall Acc. | Sem. | Temp. | Overall Acc. | |
| VideoLLaMA2-AV-7B | |||||||||
| Base | 72.3 | 82.3 | 77.3 | 70.8 | 76.1 | 72.6 | 57.2 | 43.8 | 51.7 |
| AVCD | 69.8 | 84.8 | 77.3 | 78.0 | 80.1 | 78.7 | 62.5 | 45.2 | 55.4 |
| MAD | 81.3 | 80.5 | 80.9 | 79.7 | 77.0 | 78.8 | 65.1 | 44.5 | 56.7 |
| PACD | 86.5 | 78.3 | 82.4 ( 6.6%) | 81.2 | 79.4 | 80.6 ( 11.0%) | 71.0 | 45.0 | 60.4 ( 16.8%) |
| Method | CMM | AVHBench | SVHalluc | ||||||
| Visual Dom. | Audio Dom. | Overall Acc. | Video-Driven Audio Hall. | Audio-Driven Video Hall. | Overall Acc. | Sem. | Temp. | Overall Acc. | |
| Base | 81.0 | 83.8 | 82.4 | 72.2 | 68.8 | 71.1 | 54.5 | 45.8 | 50.9 |
| Uniform | 86.0 | 85.8 | 85.9 | 76.2 | 68.6 | 73.7 | 57.0 | 46.2 | 52.6 |
| Argmax | 86.3 | 82.3 | 84.3 | 74.7 | 68.8 | 72.7 | 59.6 | 45.1 | 53.6 |
| MAD | 86.0 | 84.8 | 85.4 | 77.6 | 70.2 | 75.1 | 59.2 | 46.3 | 53.9 |
| PACD | 88.5 | 86.3 | 87.4 | 82.6 | 71.0 | 78.8 | 75.7 | 46.4 | 63.7 |
| Method | CMM | AVHBench | SVHalluc | ||||||
| Visual Dom. | Audio Dom. | Overall Acc. | Video-Driven Audio Hall. | Audio-Driven Video Hall. | Overall Acc. | Sem. | Temp. | Overall Acc. | |
| Base | 81.0 | 83.8 | 82.4 | 72.2 | 68.8 | 71.1 | 54.5 | 45.8 | 50.9 |
| Routing | 87.8 | 79.3 | 83.5 | 77.7 | 67.6 | 74.3 | 59.7 | 44.9 | 53.6 |
| RGCA | 88.3 | 85.5 | 86.9 | 81.6 | 69.8 | 77.7 | 59.8 | 45.5 | 54.0 |
| R+PBCR | 88.0 | 80.0 | 84.0 | 78.7 | 69.3 | 75.6 | 75.0 | 45.4 | 62.9 |
| PACD | 88.5 | 86.3 | 87.4 | 82.6 | 71.0 | 78.8 | 75.7 | 46.4 | 63.7 |
| Method | OmniVideoBench | FutureOmni |
| VideoLLaMA2-AV | 27.5 | 38.8 |
| VideoLLaMA2-AV+MAD | 28.3 | 36.3 |
| [][] VideoLLaMA2-AV+PACD | 31.1 ( 9.9%) | 40.0 ( 10.2%) |
| OmniVinci | 32.9 | 52.7 |
| OmniVinci+MAD | 32.5 | 51.7 |
| [][] OmniVinci+PACD | 34.8 ( 7.1%) | 53.5 ( 3.5%) |
| CMM | AVHBench | |||
| Method | Latency | GPU Mem. | Latency | GPU Mem. |
| AVCD | 1.70s | 22.6G | 1.40s | 22.7G |
| MAD | 1.41s | 20.7G | 1.40s | 20.7G |
| PACD | 1.45s | 20.7G | 1.44s | 20.7G |
| Control | Meaning and implementation role |
| Number of decoder layers included in provenance evidence aggregation. | |
| Confidence threshold for determining the preference of the routed target branch in RGCA. | |
| Confidence threshold for determining the preference of the MAD prediction in RGCA. | |
| Minimum cross-layer provenance consistency required for PBCR recovery. | |
| Minimum provenance support strength required for PBCR recovery. | |
| Confidence threshold governing selective consensus recovery in PBCR. |
| Method | CMM | AVHBench | SVHalluc | ||||||
| Visual Dom. | Audio Dom. | Overall Acc. | Video-Driven Audio Hall. | Audio-Driven Video Hall. | Overall Acc. | Sem. | Temp. | Overall Acc. | |
| VideoLLaMA2-AV-7B | |||||||||
| Base | 72.3 | 82.3 | 77.3 | 70.8 | 76.1 | 72.6 | 57.2 | 43.8 | 51.7 |
| Uniform | 77.5 | 82.8 | 80.1 | 77.1 | 77.2 | 77.1 | 61.5 | 43.9 | 54.3 |
| Argmax | 80.0 | 71.3 | 75.6 | 77.4 | 75.9 | 76.9 | 64.1 | 44.5 | 56.0 |
| MAD | 81.3 | 80.5 | 80.9 | 79.7 | 77.0 | 78.8 | 65.1 | 44.5 | 56.7 |
| Method | Sem. | Temp. | Avg. | ||||
| GSA | FGSA | CMSB | TA | TF | CMTB | ||
| VideoLLaMA2-AV-7B | |||||||
| Base | 50.0 | 57.2 | 63.1 | 50.0 | 26.8 | 51.0 | 51.7 |
| AVCD | 50.0 | 67.1 | 69.1 | 50.0 | 29.7 | 52.5 | 55.4 |
| MAD | 50.0 | 69.6 | 74.0 | 50.0 | 29.7 | 50.4 | 56.7 |
| PACD | 50.0 | 82.4 | 79.0 | 50.0 | 32.6 | 49.6 | 60.4 |
| Method | Sem. | Temp. | Avg. | ||||
| GSA | FGSA | CMSB | TA | TF | CMTB | ||
| VideoLLaMA2-AV-7B | |||||||
| Base | 50.0 | 57.2 | 63.1 | 50.0 | 26.8 | 51.0 | 51.7 |
| Uniform | 50.0 | 65.1 | 68.0 | 50.0 | 29.3 | 49.3 | 54.3 |
| Argmax | 50.0 | 60.1 | 79.0 | 50.0 | 29.0 | 51.0 | 56.0 |
| MAD | 50.0 | 69.6 | 74.0 | 50.0 | 29.7 | 50.4 | 56.7 |
| Method | CMM | AVHBench | SVHalluc | ||||||
| Visual Dom. | Audio Dom. | Overall Acc. | Video-Driven Audio Hall. | Audio-Driven Video Hall. | Overall Acc. | Sem. | Temp. | Overall Acc. | |
| VideoLLaMA2-AV-7B | |||||||||
| Base | 72.3 | 82.3 | 77.3 | 70.8 | 76.1 | 72.6 | 57.2 | 43.8 | 51.7 |
| Routing | 81.0 | 68.0 | 74.5 | 78.2 | 76.5 | 77.6 | 64.0 | 43.3 | 55.6 |
| RGCA | 84.5 | 78.8 | 81.6 | 81.1 | 79.0 | 80.4 | 65.5 | 43.9 | 56.7 |
| R+PBCR | 83.0 | 67.5 | 75.3 | 78.4 | 76.6 | 77.8 | 71.1 | 43.7 | 59.9 |
| Method | Sem. | Temp. | Avg. | ||||
| GSA | FGSA | CMSB | TA | TF | CMTB | ||
| VideoLLaMA2-AV-7B | |||||||
| Base | 50.0 | 57.2 | 63.1 | 50.0 | 26.8 | 51.0 | 51.7 |
| Routing | 50.0 | 60.1 | 78.8 | 50.0 | 31.2 | 46.0 | 55.6 |
| RGCA | 50.0 | 70.0 | 74.7 | 50.0 | 30.1 | 48.7 | 56.7 |
| R+PBCR | 50.0 | 81.5 | 80.0 | 50.0 | 32.2 | 46.3 | 59.9 |
Multimodal Hallucination
Multimodal hallucination occurs when AI systems produce claims unsupported by, or conflicting with, image, audio, video, or other input evidence.
See all 55 papers