4 papers
SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation
Yifan Wang, Zimu Wang, Suliu Qin +10
Glyph-level obfuscation can leave harmful Chinese content readable to humans while degrading automated moderation. We introduce SinoGlyphBench, a diagnostic benchmark that identifi…
GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning
Dongzhe Fan, Chuanhao Ji, Zimu Wang +2
Graph-based retrieval-augmented generation (GraphRAG) has recently emerged as a powerful paradigm for knowledge-intensive question answering, especially for tasks that require stru…
MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses
Tong Chen, Zimu Wang, Yiyi Miao +6
Medical fact-checking has become increasingly critical as more individuals seek medical information online. However, existing datasets predominantly focus on human-generated conten…
Thinker-DDM: Modeling Deliberation for Machine Translation with a Drift-Diffusion Process
Hongbin Na, Zimu Wang, Mieradilijiang Maimaiti +4
Large language models (LLMs) have demonstrated promising potential in various downstream tasks, including machine translation. However, prior work on LLM-based machine translation…