Hi! 👋🏻 I’m Yuxuan (Leo) Lu, a Ph.D. student at Northeastern University. Before that, I got my B.E. in Computer Science and Technology and Graduated with honor at Beijing University of Technology. I’m advised by Prof. Dakuo Wang. My research interest includes Human Computer Interaction and Natural Language Processing , especially in training, running and utilizing Large Language Models (LLMs) effiently and effectively. In the past, I’ve worked as Machine Learning Researcher at a joint program between LinkedIn and Microsoft Research Asia. I’ve also worked as an intern research assistant at THUNLP lab, supervised by Prof. Zhiyuan Liu(刘知远).
Picture of me, taken in The Sayram Lake (赛里木湖)
Education
I’m currently persuing my Ph.D. in Computer Science at Khoury College of Computer Sciences, Northeastern University, advised by Prof. Dakuo Wang.
I got my B.E. in Computer Science and Technology and Graduated with honor at Beijing University of Technology. Before that, I’ve finished my junior and senior high at Beijing National Day School (北京市十一学校).
Publications
2024
RECOVER: A Large Language Model-based Remote Patient Monitoring System for Postoperative GI Cancer Patients
Ziqi Yang*,
Yuxuan Lu*, Jennifer Bagdasarian, Vedant Das Swain, Ritu Agarwal, Collin Campbell, Waddah Al-Refaire, Dr Jehan El-Bayoumi, Guodong (Gordon) Gao, shara,
Dakuo Wang, and
Bingsheng Yao In Submission to IMWUT 2024, 2024
SciSpark: An Interactive Storytelling System for Young Children’s Science Education with Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)
In Submission to UIST 2024, 2024
More Samples or More Prompt Inputs? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering
In Findings of the Association for Computational Linguistics: NAACL 2024, 2024
While most existing works on LLM prompt-engineering focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can’t we design and leverage multiple prompt inputs together to further improve the LLM performance? In this work, we propose In-Context Sampling (ICS), a low-resource LLM prompt-engineering technique to produce the most confident prediction results by optimizing the construction of multiple ICL prompt inputs. Extensive experiments with two SOTA LLMs (FlanT5-XL and Mistral-7B) on three NLI datasets (e-SNLI, Multi-NLI, and ANLI) illustrate that ICS can consistently enhance LLM’s prediction performance and confidence. An ablation study suggests that a diversity-based ICS strategy may further improve LLM’s performance, which sheds light on a new yet promising future research direction.
Professional Network Matters: Connections Empower Person-Job Fit
Hao Chen,
Lun Du,
Yuxuan Lu, Qiang Fu, Xu Chen, Shi Han, Yanbin Kang, Guangming Lu, and Zi Li
In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, 2024
Online recruitment platforms typically employ Person-Job Fit models in the core service that automatically match suitable job seekers with appropriate job positions. While existing works leverage historical or contextual information, they often disregard a crucial aspect: job seekers’ social relationships in professional networks. This paper emphasizes the importance of incorporating professional networks into the Person-Job Fit model. Our innovative approach consists of two stages: (1) defining a Workplace Heterogeneous Information Network (WHIN) to capture heterogeneous knowledge, including professional connections and pre-training representations of various entities using a heterogeneous graph neural network; (2) designing a Contextual Social Attention Graph Neural Network (CSAGNN) that supplements users’ missing information with professional connections’ contextual information. We introduce a job-specific attention mechanism in CSAGNN to handle noisy professional networks, leveraging pre-trained entity representations from WHIN. We demonstrate the effectiveness of our approach through experimental evaluations conducted across three real-world recruitment datasets from LinkedIn, showing superior performance compared to baseline models.
Exploring Parent’s Needs for Children-Centered AI to Support Preschoolers’ Storytelling and Reading Activities
Proc. ACM Hum.-Comput. Interact., 2024
Interactive storytelling is vital for preschooler development. While children’s interactive partners have traditionally been their parents and teachers, recent advances in artificial intelligence (AI) have sparked a surge of AI-based storytelling technologies. As these technologies become increasingly ubiquitous in preschoolers’ lives, questions arise regarding how they function in practical storytelling scenarios and, in particular, how parents, the most critical stakeholders, experience and perceive these technologies. This paper investigates these questions through a qualitative study with 17 parents of children aged 3-6. Our findings suggest that even though AI-based storytelling technologies provide more immersive and engaging interaction, they still cannot meet parents’ expectations due to a series of interactive, functional, and algorithmic challenges. We elaborate on these challenges and discuss the possible implications of future AI-based storytelling technologies for preschoolers. We conclude by highlighting the design implications for future AI-based storytelling technologies.
Rethinking human-ai collaboration in complex medical decision making: A case study in sepsis diagnosis
Shao Zhang, Jianing Yu,
Xuhai Xu, Changchang Yin,
Yuxuan Lu,
Bingsheng Yao, Melanie Tory, Lace M Padilla, Jeffrey Caterino, Ping Zhang, and others
In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI ’24), 2024
From Dark Data to Open Data: Challenges and Practices for Data Integrators of Data-Driven Open Science Projects in Geoscience
In Submission to CSCW 2025, 2024
2023
Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks
arXiv preprint arXiv:2311.09825, 2023
Large Language Models (LLMs) have demonstrated considerable advances, and several claims have been made about their exceeding human performance. However, in real-world tasks, domain knowledge is often required. Low-resource learning methods like Active Learning (AL) have been proposed to tackle the cost of domain expert annotation, raising this question: Can LLMs surpass compact models trained with expert annotations in domain-specific tasks? In this work, we conduct an empirical experiment on four datasets from three different domains comparing SOTA LLMs with small models trained on expert annotations with AL. We found that small models can outperform GPT-3.5 with a few hundreds of labeled data, and they achieve higher or similar performance with GPT-4 despite that they are hundreds time smaller. Based on these findings, we posit that LLM predictions can be used as a warmup method in real-world applications and human experts remain indispensable in tasks involving data annotation driven by domain-specific knowledge.
FairytaleCQA: Integrating a Commonsense Knowledge Graph into Children’s Storybook Narratives
arXiv preprint arXiv:2311.09756, 2023
AI models (including LLM) often rely on narrative question-answering (QA) datasets to provide customized QA functionalities to support downstream children education applications; however, existing datasets only include QA pairs that are grounded within the given storybook content, but children can learn more when teachers refer the storybook content to real-world knowledge (e.g., commonsense knowledge). We introduce the FairytaleCQA dataset, which is annotated by children education experts, to supplement 278 storybook narratives with educationally appropriate commonsense knowledge. The dataset has 5,868 QA pairs that not only originate from the storybook narrative but also contain the commonsense knowledge grounded by an external knowledge graph (i.e., ConceptNet). A follow-up experiment shows that a smaller model (T5-large) fine-tuned with FairytaleCQA reliably outperforms much larger prompt-engineered LLM (e.g., GPT-4) in this new QA-pair generation task (QAG). This result suggests that: 1) our dataset brings novel challenges to existing LLMs, and 2) human experts’ data annotation are still critical as they have much nuanced knowledge that LLMs do not know in the children educational domain.
Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture
Bingsheng Yao,
Ishan Jindal,
Lucian Popa,
Yannis Katsis, Sayan Ghosh, Lihong He,
Yuxuan Lu, Shashank Srivastava, Yunyao Li,
James Hendler, and
Dakuo Wang In Findings of the Association for Computational Linguistics: EMNLP 2023, Dec 2023
Real-world domain expertsD (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support human annotators mostly focus on the label while neglecting the natural language explanation of a data point. This work proposes a novel AL architecture to support experts’ real-world need for label and explanation annotations in low-resource scenarios. Our AL architecture leverages an explanation-generation model to produce explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a novel data diversity-based AL sampling strategy that benefits from the explanation annotations. Automated and human evaluations demonstrate the effectiveness of incorporating explanations into AL sampling and the improved human annotation efficiency and trustworthiness with our AL architecture. Additional ablation studies illustrate the potential of our AL architecture for transfer learning, generalizability, and integration with large language models (LLMs). While LLMs exhibit exceptional explanation-generation capabilities for relatively simple tasks, their effectiveness in complex real-world tasks warrants further in-depth study.
Improving Biomedical Question Answering by Data Augmentation and Model Weighting
Yongping Du, Jingya Yan, Yuxuan Lu, Yiliang Zhao, and Xingnan Jin
IEEE/ACM Transactions on Computational Biology and Bioinformatics, Dec 2023
2022
Contextual Embedding and Model Weighting by Fusing Domain Knowledge on Biomedical Question Answering
Yuxuan Lu, Jingya Yan, Zhixuan Qi, Zhongzheng Ge, and Yongping Du
In Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, Dec 2022
Biomedical Question Answering aims to obtain an answer to the given question from the biomedical domain. Due to its high requirement of biomedical domain knowledge, it is difficult for the model to learn domain knowledge from limited training data. We propose a contextual embedding method that combines open-domain QA model AoA Reader and BioBERT model pre-trained on biomedical domain data. We adopt unsupervised pre-training on large biomedical corpus and supervised fine-tuning on biomedical question answering dataset. Additionally, we adopt an MLP-based model weighting layer to automatically exploit the advantages of two models to provide the correct answer. The public dataset biomrc constructed from PubMed corpus is used to evaluate our method. Experimental results show that our model outperforms state-of-the-art system by a large margin.
2021
Dual Model Weighting Strategy and Data Augmentation in Biomedical Question Answering
Yongping Du, Jingya Yan, Yiliang Zhao, Yuxuan Lu, and Xingnan Jin
In 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Dec 2021
Research Experience
My current research fields includes data annotation and optimizing LLMs.
Before that, I’ve worked as Machine Learning Researcher at a joint program between LinkedIn and Microsoft Research Asia where I do study about LinkedIn’s social network data. I’ve also worked as an intern research assistant at THUNLP lab, supervised by Prof. Zhiyuan Liu(刘知远). My research area there includes Knowledge Embedding.
Open source communities
I’ve participated in many open-source communities. I’m the maintainer of the VSCode extension LaTeX-Utilities, and I’m the founder and maintainer of the EduOJ project. Furthermore, I’ve contributed to many open-source projects, like GitLab, UniversalOJ, OI-Wiki, nix and others.
I’ve participated as mentor and community leader in the Open Source Promotion Plan 2021. All my 3 students successfully finished their projects. I’ve participated as a student in the OSPP 2020 in the UniversalOJ community, and successfully finished my project.
Learn more about my open-source experience at here.