Skip to content

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access 2026

Metric-Driven Reinforcement Learning for Object Hallucination Reduction in LVLM-Based Image Captioning

A reinforcement learning framework to mitigate object hallucination in LVLM-based image captioning, driven entirely by natural language processing (NLP) metrics, and can enhance caption quality by incorporating complementary evaluation metrics such as BERTScore and METEOR.

Thanh Nguyen, Hee Suk Yoon, T. Luu et al. · 0 citations