7 papers
KBE-DME: Dynamic Multimodal Evaluation via Knowledge Enhanced Benchmark Evolution
Junzhe Zhang, Huixuan Zhang, Xiaojun Wan
The rapid progress of multimodal large language models (MLLMs) calls for more reliable evaluation protocols. Existing static benchmarks suffer from the potential risk of data conta…
Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models
Zhenliang Zhang, Junzhe Zhang, Xinyu Hu +2
Large language models (LLMs) have achieved remarkable success in various tasks, yet they remain vulnerable to faithfulness hallucinations, where the output does not align with the…
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
Zhenliang Zhang, Xinyu Hu, Huixuan Zhang +2
Large language models (LLMs) excel at various natural language processing tasks, but their tendency to generate hallucinations undermines their reliability. Existing hallucination…
How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models
Huixuan Zhang, Junzhe Zhang, Xiaojun Wan
With the rapid development of text-to-vision generation diffusion models, classifier-free guidance has emerged as the most prevalent method for conditioning. However, this approach…
MINOS: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text
Junzhe Zhang, Huixuan Zhang, Xinyu Hu +4
Evaluation is important for multimodal generation tasks, while traditional multimodal evaluation metrics suffer from several limitations. With the rapid progress of MLLMs, there is…
C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation
Xu Zhang, Zhifei Liu, Jiahao Wang +4
Despite the rapid advancement of large language models, they remain highly susceptible to generating hallucinations, which significantly hinders their widespread application. Hallu…