Publications (4)
SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
Xiaqiang Tang, Yi Wang, Keyu Hu +5
Retrieval-Augmented Generation (RAG) systems require Large Language Models (LLMs) to generate responses that are faithful to the retrieved context. However, faithfulness hallucinat…
Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction
Ziyuan Zhu, Keyu Hu, Zhifei Chen +10
Reconstructing continuous physical fields from sparse measurements is a central inverse problem, but data-driven generative models can produce states that violate governing dynamic…
CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models
Xiaqiang Tang, Jian Li, Keyu Hu +5
Faithfulness hallucinations are claims generated by a Large Language Model (LLM) not supported by contexts provided to the LLM. Lacking assessment standards, existing benchmarks fo…
When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification
Zirui Pang, Haosheng Tan, Yuhan Pu +4
Image classification benchmark datasets such as CIFAR, MNIST, and ImageNet serve as critical tools for model evaluation. However, despite the cleaning efforts, these datasets still…