MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
Researchers propose HEAL, a method that reduces multimodal LLM hallucinations by calibrating information distribution drift in synergy attention heads.
A paper introduces HEAL (Head-lEvel information disentAnglement and caLibration), a technique to identify and mitigate hallucinations in multimodal large language models. It uses causal noise intervention and counterfactual Difference-in-Differences to disentangle head information distribution, finding hallucinations occur when distribution drifts from equilibrium in synergy heads. HEAL injects dynamic calibration factors into synergy head value vectors to steer outputs toward factual evidence, reducing hallucinations across multiple MLLMs.
- HEAL filters causally redundant heads via causal noise intervention on multi-head outputs.
- Counterfactual Difference-in-Differences categorizes heads into four information types.
- Hallucinations tied to distribution drift in synergy heads, not modality-specific head counts.
- Dynamic calibration factors injected into synergy head value vectors reduce hallucinations.
From the original article
1 min read at huggingface.co
Multimodal Large Language Models (MLLMs) often struggle with hallucinations, thus hindering their reliable practical applications. Existing attention-based mitigation methods mainly rely on indirect signals (e. g.
By Meng'en Qin, Junye Chen, Jucheng Liu · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.