OmniConfess: Training-Free Token-Level Confessions Mitigate Omni-Modal Hallucination
Huiqiang Rong · hf · 2026-10-06
OmniConfess is a training-free method for mitigating hallucinations in omni-modal LLMs spanning text, image, audio, and video.
- How it works: It fixes a candidate response and re-scores it at token resolution under controlled channel-wise evidence interventions, producing a structured token-by-channel "confession" that reveals the response's evidential dependence—then preserves grounded content and corrects commitments driven by irrelevant or contradictory evidence.
- Evaluation: The authors also build OmniHalluBench, a 3,540-example benchmark from six datasets across modalities and both judgment and free-form generation settings. Experiments show consistent hallucination mitigation. Code and benchmark are public.
More from Research
- Subsampling and extrapolation keep the Mandelbrot area estimate unbiased near the boundary — geoffreyirving · 2026-10-06
- New estimate sits 6.5e-9 below Hsing Lo's 2025 value; reproduction suggests the gap is a fluctuation — geoffreyirving · 2026-10-06
- Claude-assisted CUDA compute pins Mandelbrot set area to 1.506591883653, 60x tighter than 2012 record — geoffreyirving · 2026-10-06
- Group-Evolving Agents: a new paradigm where the unit of agent self-improvement is a group — xwang_lk · 2026-10-06
- SLIM paper at COLM: design principles for long-horizon agentic search systems — xiye_nlp · 2026-10-06
- The Nobel optogenetics drama: forgotten inventor Zhuo-Hua Pan had the stronger claim — _onionesque · 2026-10-06