YCYihang Cheng

Yihang Cheng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yihang Cheng has a total of 29 co-authors. Here are the top co-authors by number of shared publications:

  • Chuan Qin

    Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China

    3 shared publications
  • Hengshu Zhu

    Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China

    3 shared publications
  • Hui Xiong

    The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and The Hong Kong University of Science and Technology, Hong Kong SAR, China

    2 shared publications
  • Meng Xiao

    Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and DUKE-NUS Medical School, National University of Singapore, Singapore, Singapore

    2 shared publications
  • Xi Zhang

    College of Management and Economics, Tianjin University, Tianjin, China

    2 shared publications
  • Boya Pan

    Computer Network Information Center, Chinese Academy of Sciences, Beijing, China

    1 shared publication

Latest Publications

  • Open Access

    BioHarness: substrate-aware evidence assembly for biomedical question answering across literature, knowledge bases, and biological atlases

    by Meng Xiao, Chuan Qin, Jinmiao Chen, Yihang Cheng, Yuanchun Zhou, Hengshu Zhu

    Motivation: Biomedical question answering often requires evidence beyond topically retrieved literature, including gene alias resolution, database identifier normalization, and atlas-derived biological measurements. However, existing retrieval-augmented generation (RAG) systems typically follow a fixed workflow and lack an explicit mechanism for deciding when retrieved text is sufficient, when biomedical entity mapping is needed, or when executable evidence assembly over structured measurements should be invoked. This motivates a substrate-aware large language model (LLM) harness that selectively assembles sufficient evidence by combining literature retrieval, biomedical entity mapping, and access to atlas-derived measurements. Results: We introduce BioHarness, an LLM harness for staged biomedical evidence assembly across literature retrieval, biomedical entity-mapping resources, and atlas-derived structured measurements. Across 22 123 biomedical QA items spanning seven answer formats, BioHarness improves the pooled score from 62.2 to 67.2 over the strongest baseline. Ablations, case studies, and backbone-scaling analyses show that these gains arise from repairing evidence-substrate mismatches through reranking, entity grounding, and structured measurement access, rather than from indiscriminately invoking more reasoning steps, retrieving additional literature, or relying on a particular answer-model scale. Comparisons with the frontier models and harness show that BioHarness, despite using an open-weight backbone with only 3B active parameters, approaches frontier-level performance on selected literature QA tasks and outperforms frontier harnesses without web access on biomedical identifier and locus lookup. Availability and implementation: The source code, reproducible benchmarking scripts, and processed benchmark data required to reproduce all results in this study are publicly available under an open-source license, together with the exat configuration, model versions, and decoding settings used in our experiments. In addition, we developed a prototype web demo (https://xcompass.scimatrix.cn/) that illustrates how BioHarness can be used in an interactive biomedical QA setting.

  • Open Access

    SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models

    by Chuan Qin, Xin Chen, Chengrui Wang, Pengmin Wu, Yihang Cheng, Jingyi Zhao, Meng Xiao, Xiangchao Dong, Qingqing Long, Boya Pan, et al.


  • Top Cited Papers

    A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics

    by Chuan Qin, Le Zhang, Yihang Cheng, Rui Zha, Dazhong Shen, Qi Zhang, Xi Chen, Ying Sun, Chen Zhu, Hengshu Zhu, et al.

    In today’s competitive and fast-evolving business environment, it is critical for organizations to rethink how to make talent-related decisions in a quantitative manner. Indeed, the recent development of big data and artificial intelligence (AI) techniques has revolutionized human resource management (HRM). The availability of large-scale talent and management-related data provides unparalleled opportunities for business leaders to comprehend organizational behaviors and gain tangible knowledge from a data science perspective, which, in turn, delivers intelligence for real-time decision-making and effective talent management for their organizations. In the last decade, talent analytics has emerged as a promising field in applied data science for HRM, garnering significant attention from AI communities and inspiring numerous research efforts. To this end, we present an up-to-date and comprehensive survey on AI technologies used for talent analytics in the field of HRM. Specifically, we first provide the background knowledge of talent analytics and categorize various pertinent data. Subsequently, we offer a comprehensive taxonomy of relevant research efforts, categorized based on three distinct application-driven scenarios at different levels: talent management, organization management, and labor market analysis. In conclusion, we summarize the open challenges and potential prospects for future research directions in the domain of AI-driven talent analytics.


  • Lender retention of online prosocial lending: a self-determination perspective

    by Xi Zhang, Yihang Cheng, Juan Liu, Hongke Zhao, Dongming Xu, Yulong Li

    Purpose: Prosocial lending in online crowdfunding has flourished in recent years, and it has become a new way to fundraise for philanthropy. However, there is almost a 70% user attrition rate in crowdfunding. The purpose of this study is to understand what the lender’s lending experience and social connection influence lender retention of online prosocial lending from a self-determination perspective.Design/methodology/approach: Drawing on self-determination theory (SDT), this research utilizes a quantifiable method for factors of the lender's lending experience and social connection. Additionally, the research constructs economic models to explore the impacts of these factors acting as the necessary conditions for basic psychological needs on lender retention, using a large-scale sample of over 380,000 lenders from Kiva.Findings: The results indicate that, from the lender's lending experience aspect, the loan narratives with more profit language in the last lending and the failure of past participation are negatively related to lender retention. Regarding the lender's social connection aspect, their friends or small lending teams are positively related to lender retention, while whether they are invited and lending team size show negative influence. Furthermore, results indicate the moderating effects of the disclosure of lending motivation.Originality/value: This research explores the mechanism of lender retention of online prosocial lending, providing a self-determination perspective about how previous experience influences long-term lending behavior. The study offers significant implications for the literature on online philanthropy, SDT and user retention of online platforms. At the same time, the study provides an understanding of the effects of different aspects of SDT.


  • Open Access

    Inferring the Student Social Loafing State in Collaborative Learning with a Hidden Markov Model

    by Xi Zhang, Shan Jiang, Yihang Cheng

    With the increasingly prevailing usage of Information and Communication technologies (ICT) in collaborative learning, students can cooperate with others online easily, in spite of the restriction of time and location. Social loafing, a common phenomenon in collaborative work, has negative effect on team performance, especially on the individual's knowledge sharing behavior. In recent years, there are also some researches pointing out that social loafing is a kind of hidden and unobservable behavior. In this study, we propose a research model based on the stimulus-organism-response (S-O-R) framework and build a hidden Markov model (HMM) to infer the student's unobservable social loafing state. We collect real world behavior data from an online collaborative course from Nov 11th 2016 to Dec 21th 2016.The dataset includes more than 1200 knowledge sharing records from 150 students on Slack. Our research is expected to contribute in both academic study and managerial implications on how to set up a collaborative team.