Megadose AI progress, ranked and analyzed.

MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads

· HF Daily Papers ·
The paper ties MLLM hallucinations to drift inside “synergy heads,” not simply to weak visual or language attention.

The authors propose HEAL, a head-level method that uses causal noise intervention and counterfactual Difference-in-Differences to sort attention heads by information behavior. Their analysis says hallucinations emerge when synergy heads move away from a “healthy equilibrium” in how they distribute information. HEAL then calibrates the value vectors in those heads to regulate visual-language dependencies and push outputs toward factual evidence. The paper reports reduced hallucinations across multiple MLLMs. HF Daily Papers' note

score 4

Categories: Research