HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
This addresses a critical reliability issue for users of vision-language models, though it is an incremental improvement on existing decoding techniques.
The paper tackles object hallucinations in large vision-language models by introducing HALC, a decoding algorithm that reduces hallucinations while preserving text generation quality, outperforming state-of-the-art methods across four benchmarks.
While large vision-language models (LVLMs) have demonstrated impressive capabilities in interpreting multi-modal contexts, they invariably suffer from object hallucinations (OH). We introduce HALC, a novel decoding algorithm designed to mitigate OH in LVLMs. HALC leverages distinct fine-grained optimal visual information in vision-language tasks and operates on both local and global contexts simultaneously. Specifically, HALC integrates a robust auto-focal grounding mechanism (locally) to correct hallucinated tokens on the fly, and a specialized beam search algorithm (globally) to significantly reduce OH while preserving text generation quality. Additionally, HALC can be integrated into any LVLMs as a plug-and-play module without extra training. Extensive experimental studies demonstrate the effectiveness of HALC in reducing OH, outperforming state-of-the-arts across four benchmarks.