一作ACL 2026Poster· Natural Language Processing
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
Tianyi Niu · Justin Chen · Genta Indra Winata · Shi-Xiong Zhang · Supriyo Chakraborty · Sambit Sahu · Yue Zhang · Elias Stengel-Eskin · Mohit Bansal
摘要
Large Language Model (LLM) routers dynamically select optimal models for given inputs. Existing approaches typically assume access to ground-truth labeled data, which is often unavailable in practice, especially when user request distributions are heterogeneous and unknown. We introduce Routing w...
评测与基准OpenReview 项目页