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

Xiaozhong Liu

ACL 2026×7AAAI 2026×3ICLR 2026检索与知识社会与人本多模态推理评测与基准
新星分资深
42
一作贡献0
核心/参与37
方向广度16
合作网络12
0 一作 · 11 篇 · ACL 2026 / AAAI 2026 / ICLR 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

11
作者位次 #2/3ACL 2026Poster· Natural Language Processing

P ub M ed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering

Yiqing Zhang · Xiaozhong Liu · Fabricio Murai

摘要

Trustworthy biomedical question answering (QA) systems must not only provide accurate answers but also justify them with current, verifiable evidence. Retrieval-augmented approaches partially address this gap but lack mechanisms to iteratively refine poor queries, whereas self-reflection methods...

检索与知识社会与人本评测与基准OpenReview 项目页
作者位次 #9/9ACL 2026Poster· Natural Language Processing

L e C o D e: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation

Weikang Yuan · Kaisong Song · Zhuoren Jiang · Junjie Cao · Yujie Zhang · Jun Lin · Kun Kuang · Ji Zhang · Xiaozhong Liu

摘要

Legal consultation is essential for safeguarding individual rights and ensuring access to justice, yet remains costly and inaccessible to many individuals due to the shortage of professionals. While recent advances in Large Language Models (LLMs) offer a promising path toward scalable, low-cost l...

检索与知识评测与基准社会与人本OpenReview 项目页
作者位次 #5/5ACL 2026Poster· Natural Language Processing

"Excuse me, may I say something..." C o L ab S cience, A Proactive AI Assistant for Biomedical Discovery and LLM -Expert Collaborations

Yang Wu · Jinhong Yu · Jingwei Xiong · Zhimin Tao · Xiaozhong Liu

摘要

The integration of Large Language Models (LLMs) into scientific workflows presents exciting opportunities to accelerate biomedical discovery. However, the reactive nature of LLMs, which respond only when prompted, limits their effectiveness in collaborative settings that demand foresight and auto...

社会与人本检索与知识强化学习与后训练OpenReview 项目页
作者位次 #5/8ACL 2026Findings· Findings of ACL

" I Don’t Know What to Say": A Fact-Filling Questionnaire Method to Help Non-Experts Talk to L egal AI Assistant

Yuting Huang · Yiquan Wu · Meitong Guo · Ang Li · Xiaozhong Liu · Keting Yin · Fei Wu · Kun Kuang

摘要

Artificial intelligence has become increasingly prevalent in the legal domain. However, LegalAI systems often struggle with vague user queries that lack essential legal details, leading to suboptimal performance in practical applications. To address this challenge, we propose FactFiller, a novel...

检索与知识社会与人本多模态OpenReview 项目页
作者位次 #8/8ACL 2026Findings· Findings of ACL

Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition

Rujing Yao · Yufei Shi · Yang Wu · Ang Li · Zhuoren Jiang · XiaoFeng Wang · Haixu Tang · Xiaozhong Liu

摘要

Cloud-hosted Large Language Models (LLMs) offer unmatched reasoning capabilities and dynamic knowledge, yet submitting raw queries to these external services risks exposing sensitive user intent. Conversely, relying exclusively on trusted local models preserves privacy but often compromises answe...

安全社会与人本理论与学习动力学OpenReview 项目页
作者位次 #6/6ACL 2026Findings· Findings of ACL

From Individual Excellence to Collective Sustainability: Seeking Strategic Equilibrium in Proactive Multi-Agent Teams

Tong Zhang · Yang Wu · Yufei Shi · Rujing Yao · Zhuoren Jiang · Xiaozhong Liu

摘要

In heterogeneous scientific teams, proactive team agents can serve as effective assistants regarding the research progress of the project. However, proactive agents always suffer from collaborative myopia: a greedy optimization for immediate task accuracy which ignore the long-term goal of team s...

智能体与工具推理多模态OpenReview 项目页
作者位次 #7/8ACL 2026Findings· Findings of ACL

LLM s as Lab Engineers: A Benchmark for Analytical Method Lifecycle Management

Xiaoyi Chen · Mahsa Monshizadeh · Chaoqi Zhang · Jianjun Lang · Yang Wu · Genevieve Mortensen · Xiaozhong Liu · Haixu Tang

摘要

We introduce ChemBench, a comprehensive benchmark for evaluating LLMs’ capabilities in analytical chemistry scenarios. Unlike existing benchmarks focused on factual knowledge, ChemBench assesses model abilities to provide contextualized, practical guidance for complex analytical chemistry challen...

检索与知识推理评测与基准OpenReview 项目页

常见合作者