3 papers
cs.CV2025
Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding
Jinlin Li, Yuran Wang, Yifei Yuan +5
Large Vision-Language Models (LVLMs) have recently achieved impressive results in multimodal tasks such as image captioning and visual question answering. However, they remain pron…
cs.CL2025
From Retrieval to Generation: Unifying External and Parametric Knowledge for Medical Question Answering
Lei Li, Xiao Zhou, Yingying Zhang +1
Medical question answering (QA) requires extensive access to domain-specific knowledge. A promising direction is to enhance large language models (LLMs) with external knowledge ret…
cs.IR2025
Leave No One Behind: Enhancing Diversity While Maintaining Accuracy in Social Recommendation
Lei Li, Xiao Zhou
Social recommendation, which incorporates social connections into recommender systems, has proven effective in improving recommendation accuracy. However, beyond accuracy, diversit…