# OmniHalluc-L: Counterfactual Benchmarking and Modality-Perturbation Reliability Calibration for Long-Form Omni Hallucination

arXiv: https://arxiv.org/abs/2606.03614 · HTML: https://mlsanity.com/paper/2606.03614/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2026.

## Built on by (most cited first, 3 of 3)

- [Whose record is this? Diagnosing and authorizing record use in personalized multimodal models](https://mlsanity.com/paper/2609.04801/) (2026)
- [Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents](https://mlsanity.com/paper/2609.28564/) (2026)
- [OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination](https://mlsanity.com/paper/2610.02999/) (2026)

## Abstract (arXiv)

Long-video Omni assistants often fail not by inventing content, but by misbinding real evidence: they hear the right utterance and see the right event, yet attach it to the wrong speaker, moment, or modality. These almost-true errors evade standard video QA because local evidence remains valid, so item-level scoring can reward both a supported claim and its near-counterfactual. We introduce a counterfactual event-binding protocol that constructs paired supported/counterfactual claims from the same audio-visual event evidence and evaluates them by strict-pair accuracy. We instantiate it as bench, a benchmark for long-video Omni hallucination, with 3,600 single-claim QA items from 638 long-form videos averaging 24.16 minutes and covering 256.87 hours. Under this protocol, open-weight Omni models remain weak at pair-level binding: Qwen2.5-Omni-7B reaches 32.06% and Qwen3-Omni-Instruct reaches 41.55%, versus 76.54% for a closed-source reference. To narrow this gap without updating the backbone, we propose method, Modality-Perturbation Reliability Calibration, a frozen-backbone framework that selects audio-negative probes within video-level folds and fuses their response shifts with native audio-visual confidence into per-claim support estimates. method lifts Qwen2.5-Omni-7B to 36.22% and Qwen3 to 51.09% on bench, and improves target-adapted MCQ accuracy on OmniVideoBench (+2.20) and WorldSense (+1.51) with Qwen3.