Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
This addresses factual inaccuracies in video descriptions for applications like automated captioning, though it is incremental as it builds on prior work for static images.
The paper tackles the problem of object and action hallucinations in multimodal LLMs for video captioning by proposing the SANTA framework, which uses self-augmented contrastive alignment to improve faithfulness, resulting in superior performance on hallucination benchmarks.
Recent advancement in multimodal LLMs (MLLMs) has demonstrated their remarkable capability to generate descriptive captions for input videos. However, these models suffer from factual inaccuracies in the generated descriptions, causing severe hallucination issues. While prior works have explored alleviating hallucinations for static images, jointly mitigating visual object and temporal action hallucinations for dynamic videos remains a challenging and unsolved task. To tackle this challenge, we propose a Self-Augmented Contrastive Alignment (SANTA) framework for enabling object and action faithfulness by exempting the spurious correlations and enforcing the emphasis on visual facts. SANTA employs a hallucinative self-augmentation scheme to identify the potential hallucinations that lie in the MLLM and transform the original captions to the contrasted negatives. Furthermore, we develop a tracklet-phrase contrastive alignment to match the regional objects and relation-guided actions with their corresponding visual and temporal phrases. Extensive experiments demonstrate that SANTA outperforms existing methods in alleviating object and action hallucinations, yielding superior performance on the hallucination examination benchmarks.