Related papers: Shadow-Loom: Causal Reasoning over Graphical World…

Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeling, citation networks, and social graphs. Meanwhile, large language models (LLMs) have…

Large language models (LLMs) exhibit logically inconsistent hallucinations that appear coherent yet violate reasoning principles, with recent research suggesting an inverse relationship between causal reasoning capabilities and such…

Causal loop and stock and flow diagrams are broadly used in System Dynamics because they help organize relationships and convey meaning. Using the analytical work of Schoenberg (2019) to select what to include in a compressed model, this…

We interpret the predictions of any black-box structured input-structured output model around a specific input-output pair. Our method returns an "explanation" consisting of groups of input-output tokens that are causally related. These…

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an…

Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs (TAGs), which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are…

Reasoning about time and temporal relations is an integral aspect of human cognition, essential for perceiving the world and navigating our experiences. Though large language models (LLMs) have demonstrated impressive performance in many…

We present an approach for automatically generating and testing, in silico, social scientific hypotheses. This automation is made possible by recent advances in large language models (LLM), but the key feature of the approach is the use of…

Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?". The comparison of this instance before and after…

Causal structure discovery methods are commonly applied to structured data where the causal variables are known and where statistical testing can be used to assess the causal relationships. By contrast, recovering a causal structure from…

A single image can convey a compelling story through logically connected visual clues, forming Chains-of-Reasoning (CoRs). We define these semantically rich images as Storytelling Images. By conveying multi-layered information that inspires…

Prevalent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations…

Automated story generation has been one of the long-standing challenges in NLP. Among all dimensions of stories, suspense is very common in human-written stories but relatively under-explored in AI-generated stories. While recent advances…

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

Climate action is difficult to persuade because we tend to perceive climate change as remote and disconnected from daily life. Instead of traditional informational engagements, game-based interventions can create narratives that immerse the…

Real-world observational datasets and machine learning have revolutionized data-driven decision-making, yet many models rely on empirical associations that may be misleading due to confounding and subgroup heterogeneity. Simpson's paradox…

Learning causal relationships between variables is a well-studied problem in statistics, with many important applications in science. However, modeling real-world systems remain challenging, as most existing algorithms assume that the…

Storytelling aims to generate reasonable and vivid narratives based on an ordered image stream. The fidelity to the image story theme and the divergence of story plots attract readers to keep reading. Previous works iteratively improved the…

We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation. Existing works ignore the…

Research on storytelling over the last 100 years has distinguished at least two levels of narrative representation (1) story, or fabula; and (2) discourse, or sujhet. We use this distinction to create Fabula Tales, a computational framework…