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

Jiahao Zhao

ACL 2026ICLR 2026SIGIR 2026推理检索与知识评测与基准效率与系统
新星分新星
66
一作贡献30
核心/参与10
方向广度14
合作网络6
1 一作 · 3 篇 · ACL 2026 / ICLR 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 #5/8ACL 2026Findings· Findings of ACL

M eas H alu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning

Ruijun Huang · Zhiqiao Kang · Yuxuan Zhu · Junxiong Li · Jiahao Zhao · Minghuan Tan · Feng Jiang · Min Yang

摘要

The accurate extraction of scientific measurements from literature is a critical yet challenging task in AI4Science, enabling large-scale analysis and integration of quantitative research findings. However, Large Language Models (LLMs) frequently exhibit severe hallucinations, which significantly...

评测与基准检索与知识推理OpenReview 项目页
作者位次 #4/5SIGIR 2026Poster· Information Retrieval (Short)

GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation

Zhonghui Zhang · Feng Jiang · Shaowei Qin · Jiahao Zhao · Min Yang

摘要

Zero-shot single-cell cell-type annotation aims to determine a cell's type from a given set of expressed genes without any training. Existing knowledge-graph-based RAG approaches retrieve evidence by expanding from source entities and relying on iterative LLM reasoning. However, in this setting e...

检索与知识推理效率与系统OpenReview

常见合作者