---
format: "aidr-story-markdown/v1"
id: "3c063587217718e54ec7a57032b095a7ca56d4ad416d60d33fa021f3f032e507"
canonical_url: "https://aidr.today/3c063587?lang=en"
title: "Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-26T00:00:00.000Z"
category: "Research"
topics: ["llm"]
source_urls: ["https://huggingface.co/papers/2610.27103"]
summary: "Omni-Woodpecker is a training-free framework that addresses cross-modal hallucinations in Omni LLMs by identifying conflicts from complementary modality-specific views, using orthogonal decomposition to separate grounding evidence from competing priors, and adaptively rebalancing fused representations before decoding. Experiments show the method is effective and generalizes well across architectures."
---

# Omni\-Woodpecker: Hallucination Correction via Evidence\-Prior Rebalancing for Omni LLMs

> [Open the canonical story](<https://aidr.today/3c063587?lang=en>)

**Published:** 2026-10-26T00:00:00.000Z
**Category:** Research
**Topics:** llm

## Summary

Omni\-Woodpecker is a training\-free framework that addresses cross\-modal hallucinations in Omni LLMs by identifying conflicts from complementary modality\-specific views, using orthogonal decomposition to separate grounding evidence from competing priors, and adaptively rebalancing fused representations before decoding\. Experiments show the method is effective and generalizes well across architectures\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.27103>)