招聘 | IT:U奥地利跨学科创新技术大学 Prof. Yufang Hou 招聘NLP方向岗位制博士生、博士后

Prof. Dr. Yufang Hou (侯玉芳教授) 是一位自然语言处理 (NLP) 和计算语言学领域的优秀学者。她在篇章理解 (discourse processing), 计算辩论 (computational argumentation), 事实核查 (fact-checking), 学术文档处理 (scholarly document processing), 信息抽取 (information extraction) 方面具有丰富的研究经验。

侯玉芳教授将于今年11月加入奥地利跨学科创新技术大学 IT:U, 任职终身创校教授。她同时也在IBM欧洲研究院（爱尔兰）担任高级研究员。侯博士于2015年到2019年期间作为核心成员参与了IBM研究院重大挑战项目Project Debater的研发工作。此前，侯博士曾在达姆施塔特工业大学UKP实验室担任兼职高级讲师和访问教授，并作为主要导师联合指导博士生。

侯玉芳教授将领导IT:U大学的NLP实验室开展前沿的NLP 研究，开发稳健且值得信赖的 NLP 技术，以改善人机交互和人际互动，并解决现实世界中的问题。IT:U大学NLP实验室的研究重点包括大语言模型治理 (LLM governance), 跨文档 NLP (cross-document NLP), 知识与推理 (knowledge and reasoning) 以及面向教育、社会科学、人文学科和科学发现的人本化 NLP 应用 (human-centred NLP applications for education, social sciences, humanities, and scientific discovery)。

IT:U奥地利跨学科创新技术大学 (IT:U - Interdisciplinary Transformation University Austria, https://it-u.at/en/) 是欧洲首批专注于科学、商业和社会数字化转型的公立大学之一。学校提供了一种全新的数字化学习方式。通过基于项目的包容性技术教育方法，学校为来自广泛学科背景的学生提供应对全球挑战所需的数字技能。

学校位于奥地利东北部城市林茨 (Linz, Austria)。林茨是上奥地利州的首府，也是奥地利的第三大城市。它距离奥地利首都维也纳约150公里（乘火车约需1个半小时)，距离德国慕尼黑约200公里（乘火车约需3小时)。

我们邀请热爱自然语言处理 (NLP) 和机器学习的博士生和博士后加入我们的研究团队。 主要研究方向包括但不限于：

We will focus on evaluating and mitigating undesirable LLM behaviors, such as building LLM evaluation benchmarks and understanding the behaviors of LLMs with real-world knowledge conflicts.

示例论文：

1. [TACL 2024] Holmes: A Benchmark to Assess the Linguistic Competence of Language Models

   https://arxiv.org/abs/2404.18923

2. [NeurIPS 2024 D&B] WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia

   https://arxiv.org/abs/2406.13805

We aim to combine argument mining and fact-checking technologies to combat real-world misinformation, such as detecting health and science misinformation.

示例论文：

1. [EMNLP 2022] Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation

   https://aclanthology.org/2022.emnlp-main.397/

2. [ACL 2024] Missci: Reconstructing Fallacies in Misrepresented Science

   https://aclanthology.org/2024.acl-long.240/

   
   

The goal is to develop reliable cross-document NLP techniques to support scientific research activities, including generating slides from scientific papers, building scientific leaderboards, generating citation text, synthesizing biomedical studies, and analyzing causal relations between scientific research concepts.

示例论文：

1. [NAACL 2021] D2S: Document-to-Slide Generation Via Query-Based Text Summarization

   https://aclanthology.org/2021.naacl-main.111/

2. [ACL 2019] Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction

   https://aclanthology.org/P19-1513/

3. [ACL 2024] Systematic Task Exploration with LLMs: A Study in Citation Text Generation

   https://aclanthology.org/2024.acl-long.265

4. [ACL SRW 2024] Beyond Abstracts: A New Dataset, Prompt Design Strategy and Method for Biomedical Synthesis Generation

   https://aclanthology.org/2024.acl-srw.42/

5. [EMNLP 2023] A Diachronic Analysis of Paradigm Shifts in NLP Research: When, How, and Why?

   https://aclanthology.org/2023.emnlp-main.142

   
   

We aim to develop techniques that can effectively represent both explicit and implicit knowledge to perform complex reasoning tasks in situated contexts, such as designing a fallacious reasoning framework for misrepresented science and building an argumentation knowledge graph.

示例论文：

1. [ACL 2024] Missci: Reconstructing Fallacies in Misrepresented Science

   https://aclanthology.org/2024.acl-long.240/

2. [AAAI 2020] End-to-End Argumentation Knowledge Graph Construction

   https://ojs.aaai.org/index.php/AAAI/article/view/6231

招聘岗位： 三位博士生和两位博士后

IT:U Phd and PostDoc Program

截止日期： 2024年11月30日

招聘官网详见：

https://it-u.at/en/research/research-groups/natural-language-processing/

• 4年全日制岗位，税前月薪为 €3,578.80，每年发放14个月薪资。