Mitigating Dialogue Hallucination for Large Multi-modal Models via Adversarial Instruction Tuning

arXiv:2403.10492v1 Announce Type: new
Abstract: Mitigating hallucinations of Large Multi-modal Models(LMMs) is crucial to enhance their reliability for general-purpose assistants. This paper shows that such hallucinations of LMMs can be significantly exacerbated by preceding user-system dialogues. To precisely measure this, we first present an evaluation benchmark by extending popular multi-modal benchmark datasets with prepended hallucinatory dialogues generated by our novel Adversarial Question Generator, which can automatically generate image-related yet adversarial dialogues by adopting adversarial attacks on LMMs. On our benchmark, …

abstract adversarial arxiv assistants benchmark cs.cv dialogue evaluation general hallucination hallucinations lmms modal multi-modal paper popular reliability shows type via