Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
Mila - Québec AI Institute(魁北克人工智能研究所);University of Montréal(蒙特利尔大学);HEC Montréal(蒙特利尔HEC商学院);University of Ottawa(渥太华大学);National Research Council of Canada(加拿大国家研究理事会);CIFAR AI Chair(CIFAR人工智能 chair)
Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expression responses for unobserved conditions. A promising recent direction leverages large language models (LLMs) as "virtual cell" simulators-using stepwise, knowledge-grounded mechanistic reasoning to infer differential expression-pointing toward an interpretable, knowledge-driven paradigm that transcends purely data-driven approaches. However, we find that plausibility is not prediction: despite producing biologically plausible explanations, these methods fail to capture perturbation-specific effects: systematically overestimating differential expression, often underperforming a simple gene-frequency baseline in aggregate evaluations, and collapsing to chance-level performance at the per-gene level. This reveals a reliance on intrinsic gene response tendencies rather than true perturbation reasoning. We trace this failure to how evidence is presented: existing methods evaluate perturbation-gene pairs in isolation, without exposing how related perturbations differ in their effects on the same gene. To address this limitation, we introduce CORE (Contrastive Organization of Relational Evidence), which reframes prediction as a comparison task by organizing evidence into positive and negative outcomes from related perturbations. Using a biomedical knowledge graph for evidence retrieval, CORE improves calibration and substantially boosts perturbation-specific prediction in both LLM-based and non-LLM settings: for example, on drug-perturbation data, CORE-Reasoning improves Qwen3.5-9B aggregate metrics by up to 28.6%, while on generic perturbation data, CORE-Voting raises macro-per-gene AUROC from chance to 0.703 in average across four cell lines. This highlights contrastive evidence organization as essential to reliable LLM-based perturbation reasoning
Estimating Commonsense Plausibility through Semantic Shifts
CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China(中国科学院网络数据科学与技术重点实验室,计算技术研究所,中国科学院,北京,中国);University of Chinese Academy of Sciences, Beijing, China(中国科学院大学,北京,中国)
CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection
School of Informatics, Xiamen University(厦门大学信息学院);China Academy of Information and Communications Technology(中国信息通信技术研究院);AI Transcend Pte. Ltd.(AI Transcend有限公司)
scI2CL: Effectively Integrating Single-cell Multi-omics by Intra- and Inter-omics Contrastive Learning
School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院);College of Computer Science and Artificial Intelligence, Fudan University(复旦大学计算机科学与人工智能学院)
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
Valence Labs;University of Toronto(多伦多大学);Vector Institute(矢量研究所);University of British Columbia(不列颠哥伦比亚大学);Université de Montréal(蒙特利尔大学);Mila- Quebec AI Institute(米拉-魁北克人工智能研究所)
scAGC: Learning Adaptive Cell Graphs with Contrastive Guidance for Single-Cell Clustering
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China(上海可信计算实验室,华东师范大学);Department of Computational Biology, Mohamed bin Zayed University of AI, Abu Dhabi, UAE(计算生物学系,马尔代夫人工智能大学);Department of Computer Science, Stevens Institute of Technology, Hoboken, USA(计算机科学系,史蒂文斯理工学院);College of Electronics and Information Engineering, Tongji University, Shanghai, China(电子信息工程学院,同济大学)
Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between Proteins
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院);Institute of Artificial Intelligence, Huazhong University of Science and Technology(华中科技大学人工智能研究院);Hubei Key Laboratory of Brain-Inspired Intelligent Systems, Huazhong University of Science and Technology(华中科技大学湖北省类脑智能系统重点实验室);Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology), Ministry of Education(华中科技大学图像信息处理与智能控制教育部重点实验室)
Contrastive Cycle Adversarial Autoencoders for Single-cell Multi-omics Alignment and Integration
Department of Computer Science and Engineering, CUHK(香港中文大学计算机科学与工程系);The CUHK Shenzhen Research Institute(香港中文大学深圳研究院);Department of Mathematics, CUHK(香港中文大学数学系);Department of Information Engineering, CUHK(香港中文大学信息工程系);Purdue University(普渡大学);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)