3 papers
cs.CL2025
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…
cs.CL2025
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…
cs.CV2025
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…