Search Results

Students are increasingly relying on Generative AI (GAI) to support their writing—a key pedagogical practice in education. In GAI-assisted writing, students can delegate core cognitive tasks (e.g., generating ideas and turning them into sentences) to GAI ...

In software development, software fault prediction (SFP) models aim to identify code sections with a high likelihood of faults before the testing process. SFP models achieve this by analyzing data about the structural properties of the software’s previous ...

Recommender systems are important and powerful tools for various personalized services. Traditionally, these systems use data mining and machine learning techniques to make recommendations based on correlations found in the data. However, relying solely ...

Understanding expressions is vital for deciphering human behavior, and nowadays, end-to-end trained black box models achieve high performance. Due to the black-box nature of these models, it is unclear how they behave when applied out-of-...

Causal inference is used in various domains such as healthcare, economics, and political science to infer causal effects from observational data where each unit (entity) has different properties. Existing approaches often assume data completeness, ...

With the increasing interest in explainable attribution for deep neural networks, it is important to consider not only the importance of individual inputs, but also the model parameters themselves. Existing methods, such as Neuron Integrated ...

Explainability and attribution for deep neural networks remains an open area of study due to the importance of adequately interpreting the behavior of such ubiquitous learning models. The method of expected gradients [10] reduced the baseline ...

Cooperation and coordination are highly desired properties of an effective multi-agent reinforcement learning (MARL) system. Understanding cause-and-effect relationships, know an causal inference, can be exploited to promote the emergence of ...

In recent years, the rise of big data has popularized data-driven decision-making. However, the interpretability shortcomings of artificial intelligence (AI) models limit their reliability for critical decisions. This paper proposes a paradigm ...

Causal inference is a methodology to assess the impact of one variable on another by establishing a cause-and-effect relationship. This paper deals with causal inference analyses using Electronic Health Record (EHR) data from the UK Biobank. Key ...

Many previous studies have shown that Large Language Models (LLMs) are highly competent on many Natural Language Processing (NLP) tasks. However, a recent study showed the poor ability of LLMs to perform causal inference based on causal graphs and ...

In previous fact-checking methods, the common practice was to first employ cross-modal cross-retrieval to obtain relevant textual and image evidence, and then input the retrieved evidence into the model for verification. However, these methods ...

Short-video recommender systems often exhibit a biased preference to recently released videos. However, not all videos become outdated; certain classic videos can still attract user’s attention. Such bias along temporal dimension can be further ...

Developing models that are capable of answering questions of the form “How would $x$ change if $y$ had been $z$?” is fundamental to advancing medical image analysis. Training causal generative models that address such counterfactual questions, though, ...

Analyzing and predicting user information-sharing behavior on online social platforms is a crucial task in social sciences. While current prediction tasks primarily emphasize accuracy, they often neglect the underlying motivations that drive user ...

Estimating causal effects in e-commerce tends to involve costly treatment assignments which can be impractical in large-scale settings. Leveraging machine learning to predict such treatment effects without actual intervention is a standard ...

Estimating the individual treatment effect (ITE) from observational data is an important issue both theoretically and practically. While including all the pre-treatment covariates is the common practice for the inclusion of all possible ...$$

Humans engage in causal inference almost every day, however, the term ‘causation’ is still quite ambiguous, and few AI systems provide a comprehensive and satisfactory solution to causal inference. In this paper, we adopt the primary meaning of ...

In the information age, with the explosive growth of data volume, big data analysis and prediction have become central to ensuring stable operations across various industries. As hardware computing power increases and data volume continues to grow, the ...

In this paper, we demonstrate the utility of probabilistic fuzzy logic in providing a flexible and sound framework for analyzing causality. Initially, we identify a limitation associated with the conventional Average Treatment Effect (ATE) ...$$$$