作者位次 #4/5ICML 2026Poster· Deep Learning / Large Language Models
Unbiased Alignment for Large Language Models with Noisy Preferences
Jialiang Wang · Xianming Liu · Xiong Zhou · Hui Liu · Haoliang Li
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。
Jialiang Wang · Xianming Liu · Xiong Zhou · Hui Liu · Haoliang Li
Kecheng Chen · Ziru Liu · Xijia Tao · Hui Liu · Xinyu Fu · Suiyun Zhang · Dandan Tu · Lingpeng Kong · Rui Liu · Haoliang Li
Hui Liu · Bin Zou · Kecheng Chen · Jie Liu · Wenya Wang · Haoliang Li
Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet user-specific cost–performance trade-offs. However, existing routers generalize poorly in cold-start scenarios where i...
Chris Xing Tian · Weihao Xie · Zhen Chen · Hui Liu · Zhengyuan Yi · Haoliang Li · Shiqi Wang · Siwei Ma
Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning capabilities of large language models (LLMs) with external retrieval to produce domain-grounded responses. Effectively adapting RAG systems to domain-specific settings requires specialized, context-rich trainin...