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

Chengkai Liu

ACL 2026×2检索与知识强化学习与后训练效率与系统评测与基准推理
新星分贡献者
34
一作贡献0
核心/参与10
方向广度10
合作网络3
0 一作 · 2 篇 · ACL 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

2
作者位次 #3/7ACL 2026Poster· Natural Language Processing

DMR etriever: A Family of Models for Improved Text Retrieval in Disaster Management

Kai Yin · Xiangjue Dong · Chengkai Liu · Allen Lin · Lingfeng Shi · Ali Mostafavi · James Caverlee

摘要

Effective and efficient access to relevant information is essential for disaster management. However, no retrieval model is specialized for disaster management, and existing general-domain models fail to handle the varied search intents inherent to disaster management scenarios, resulting in inco...

检索与知识强化学习与后训练效率与系统OpenReview 项目页
作者位次 #4/10ACL 2026Findings· Findings of ACL

D isast QA : A Comprehensive Benchmark for Evaluating Question Answering in Disaster Management

Zhitong Chen · Kai Yin · Xiangjue Dong · Chengkai Liu · Xiangpeng Li · Bo Li · Junwei Ma · Yiming Xiao · Ali Mostafavi · James Caverlee

摘要

Accurate question answering (QA) in disaster management requires reasoning over uncertain and conflicting information, a setting poorly captured by existing benchmarks built on clean evidence. We introduce DisastQA, a rigorously verified benchmark of 3,000 expert-annotated questions (2,000 multip...

评测与基准检索与知识推理OpenReview 项目页

常见合作者