paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
S&

Shaowei Yao (Taobao &amp

KDD 2026NeurIPS 2026SIGIR 2026强化学习与后训练检索与知识对齐与偏好数据与预训练推理
新星分贡献者
65
一作贡献0
核心/参与33
方向广度16
合作网络9
0 一作 · 3 篇 · KDD 2026 / NeurIPS 2026 / SIGIR 2026

获取完整研究档案

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。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

3
作者位次 #2/15SIGIR 2026Poster· Information Retrieval (Industry)

Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevance

Tingqiao Xu · Shaowei Yao (Taobao &amp · Chenhe Dong (Taobao &amp · Chenhe Dong (Taobao &amp · Zerui Huang (Taobao &amp · Chenhe Dong (Taobao &amp · Xingxian Liu (Taobao &amp · Zerui Huang (Taobao &amp · Shengjie Sun (Taobao &amp · Chenhe Dong (Taobao &amp · Shengjie Sun (Taobao &amp · Xingxian Liu (Taobao &amp · Shengjie Sun (Taobao &amp · Bo Zheng (Taobao &amp · Shengjie Sun (Taobao &amp

摘要

Accurately estimating query-item relevance is vital for e-commerce ranking and conversion. While Large Language Models (LLMs) excel at reasoning, they often lack specialized knowledge required for long-tail or fast-evolving queries, necessitating Retrieval-Augmented Generation (RAG). However, pro...

强化学习与后训练检索与知识推理OpenReview

常见合作者