5 papers
No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs
Haojian Huang, Harold Haodong Chen, Meng Luo +6
We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. Unlike previous benchmarks th…
IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web
Hongcheng Guo, Wei Zhang, Junhao Chen +9
Recently advancements in large multimodal models have led to significant strides in image comprehension capabilities. Despite these advancements, there is a lack of the robust benc…
Kongzi: A Historical Large Language Model with Fact Enhancement
Jiashu Yang, Ningning Wang, Yian Zhao +5
The capabilities of the latest large language models (LLMs) have been extended from pure natural language understanding to complex reasoning tasks. However, current reasoning model…
Cluster-Driven Expert Pruning for Mixture-of-Experts Large Language Models
Hongcheng Guo, Juntao Yao, Boyang Wang +5
Mixture-of-Experts (MoE) architectures have emerged as a promising paradigm for scaling large language models (LLMs) with sparse activation of task-specific experts. Despite their…
DependEval: Benchmarking LLMs for Repository Dependency Understanding
Junjia Du, Yadi Liu, Hongcheng Guo +4
While large language models (LLMs) have shown considerable promise in code generation, real-world software development demands advanced repository-level reasoning. This includes un…