作者位次 #4/5ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety
MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers
Xuanjun Zong · Zhiqi Shen · Lei Wang · Yunshi Lan · yang chao
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Xuanjun Zong · Zhiqi Shen · Lei Wang · Yunshi Lan · yang chao
Xinchen Ma · Gaole He · Yunshi Lan · Weining Qian
Despite recent progress in LLMs for text style transfer, most existing methods rely on costly task-specific training and offer limited control over separating stylistic modification from content preservation. We propose Diff4TST, a diffusion-based language model that formulates text style transfe...
Qianyu Wang · Xiaoman Wang · Yuanyuan Liang · Xinyuan Li · Yunshi Lan
Grammatical error correction (GEC) systems are usually trained and evaluated on GEC benchmarks, but their performance often drops sharply once the surrounding context is slightly perturbed or extended. This indicates that the existing GEC models usually fail to understand the error patterns in th...
Wenbiao Tao · Xinyuan Li · Yunshi Lan · Weining Qian
Retrieval-Augmented Generation enhances language models by retrieving external knowledge to support informed and grounded responses. However, traditional RAG methods rely on fragment-level retrieval, limiting their ability to address query-focused summarization queries. GraphRAG introduces a grap...