Large vision-language models can produce fluent responses containing objects, attributes, or relations unsupported by the image. We study an implemented alignment pipeline that normalizes released fine-grained hallucination supervision, validates chosen-rejected preference pairs with vision-language judges, repairs rejected chosen responses, and trains LLaVA adapters with standard or severity-aware direct preference optimization. The study uses 16,143 normalized feedback records and 8,386 released preference pairs, comparing direct training with zero-shot and two-shot judged severity-margin variants. The zero-shot variant reduces Object HalBench CHAIRs from 53.00 to 36.00 and CHAIRi from 15.72 to 10.41. Across aligned models, AMBER-Hal decreases from 35.90 to 25.10-26.90, accompanied by reduced visual coverage. In contrast, the base model retains the highest valid POPE adversarial F1, 84.18 versus 83.87-83.91 after alignment. These results support benchmark-dependent reductions in generative hallucination rather than uniform superiority of severity-aware alignment. We distinguish implemented pipeline components from the preference paths used in the reported experiments and discuss the limits of attributing gains to judging, repair, or the training objective individually.
翻译:暂无翻译