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

Geyuan Zhang

ACL 2026×2ICML 2026检索与知识推理评测与基准智能体与工具效率与系统
新星分贡献者
65
一作贡献30
核心/参与5
方向广度13
合作网络9
1 一作 · 3 篇 · ACL 2026 / ICML 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 #4/4ACL 2026Poster· Natural Language Processing

Temporal Evidence Chain for Temporal Knowledge Graph Question Answering with Large Language Models

Shihao Liu · Xiaofei Zhou · Bo Wang · Geyuan Zhang

摘要

Temporal Knowledge Graph Question Answering (TKGQA) aims to answer temporal questions using knowledge from Temporal Knowledge Graphs (TKGs).Existing LLM-based TKGQA methods typically utilize RAG-based or Agent-based paradigms, yet both struggle to construct reliable temporal evidence chains. RAG-...

检索与知识推理智能体与工具OpenReview 项目页
一作ACL 2026Findings· Findings of ACL

SDC - L o RA : Singular-Subspace Drift Controlled L o RA to Mitigate Knowledge Forgetting

Geyuan Zhang · Xiaofei Zhou · Shihao Liu · Jingyuan Tian · Jizheng Ma

摘要

Knowledge forgetting is a central challenge when adapting LLMs to new tasks. Prior studies indicate that pretrained knowledge is concentrated in the principal singular subspace of pretrained weight W_0 ; so recent Low-Rank Adaptation (LoRA) variants initialize LoRA in the minor subspace to steer...

效率与系统检索与知识推理OpenReview 项目页

常见合作者