作者位次 #4/5ICML 2026Oral· Deep Learning / Large Language Models
Don't Force the Fit: Bounded Log-Likelihood Loss for Enhanced Reasoning in Large Language Models
Feng Zhao · Hong Zhang · Yu Yang · Ruilin Zhao · Guandong Xu
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。
Feng Zhao · Hong Zhang · Yu Yang · Ruilin Zhao · Guandong Xu
Feng Zhao · Yufei Wu · Xianggan Liu · Ruilin Zhao
Retrieval-Augmented Generation (RAG) was proposed to address the hallucination question of large language models (LLMs). However, the traditional RAG framework has certain limitations: for simple questions, the search results often introduce a large amount of irrelevant information; while for com...