作者位次 #15/15ACL 2026Poster· Natural Language Processing
W ild F eedback: Aligning LLM s With In-situ User Interactions And Feedback
Taiwei Shi · Zhuoer Wang · Longqi Yang · Ying-Chun Lin · Zexue He · Mengting Wan · Pei Zhou · Sujay Kumar Jauhar · Sihao Chen · Shan Xia · Hongfei Zhang · Jieyu Zhao · Xiaofeng Xu · Xia Song · Jennifer Neville
摘要
As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their resource-intensive nature, inherent subjectivity, misalignment wit...