Uncovering memorization effect in the presence of spurious correlations by Chenyu You, Haocheng Dai, Yifei Min, Jasjeet S. Sekhon, Sarang Joshi, James S. Duncan

“…Our experimental results across various architectures and benchmarks offer new insights on how neural networks encode core and spurious knowledge, laying the groundwork for future research in demystifying robustness to spurious correlation.…”
Get full text

A Data Centric HitL Framework for Conducting aSsystematic Error Analysis of NLP Datasets using Explainable AI by Ahmed El-Sayed, Aly Nasr, Youssef Mohamed, Ahmed Alaaeldin, Mohab Ali, Omar Salah, Abdullatif Khalid, Shaimaa Lazem

“…The systematic process has resulted in identifying spurious correlation, bias patterns, and other anomaly patterns in the dataset. …”
Get full text

Model-based exploration is measurable across tasks but not linked to personality and psychiatric assessments by Kristin Witte, Mirko Thalmann, Eric Schulz

“…To improve future research, we suggest simplifying common computational models and using multiple tasks to more accurately measure exploration strategies and mitigate spurious correlations arising from task-specific factors.…”
Get full text

Visual Commonsense Causal Reasoning From a Still Image by Xiaojing Wu, Rui Guo, Qin Li, Ning Zhu

“…However, in real-world scenarios, CCR is fundamentally a multisensory task and is more susceptible to spurious correlations, given that commonsense causal relationships manifest in various modalities and involve multiple sources of confounders. …”
Get full text

DiffCoRank: a comprehensive framework for discovering hub genes and differential gene co-expression in brain implant-associated tissue responses by Anirban Chakraborty, Erin K. Purcell, Michael G. Moore

“…A key innovation of our approach is false discovery rate (FDR) based selection of strongly connected genes (SCGs), by which we improve detection of strong coexpression patterns that otherwise could be lost to spurious correlations. To enhance the identification of different modules, we employ a hybrid clustering technique that combines uniform manifold approximation and projection (UMAP) with density-based spatial clustering of applications with noise (DBSCAN). …”
Get full text