相关论文: ISAAC: Auditing Causal Reasoning in Deep Models fo…

Agentic AI systems increasingly act through tools, sub-agents, and external services, but governance controls are still commonly attached to prompts, dashboards, or post-hoc documentation. This creates a structural mismatch in regulated…

Counterfactual explanations provide human-understandable reasoning for AI-made decisions by describing minimal changes to input features that would alter a model's prediction. To be truly useful in practice, such explanations must be…

Advancements in large language models (LLMs) allow them to address diverse questions using human-like interfaces. Still, limitations in their training prevent them from answering accurately in scenarios that could benefit from multiple…

Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversarial vulnerability and proposes Causal Intervention by…

Adverse drug-drug interactions (DDIs) remain a leading cause of morbidity and mortality. Identifying potential DDIs during the drug design process is critical for patients and society. Although several computational models have been…

Nonlinear causal discovery from observational data imposes strict identifiability assumptions on the formulation of structural equations utilized in the data generating process. The evaluation of structure learning methods under assumption…

In many areas, we have well-founded insights about causal structure that would be useful to bring into our trained models while still allowing them to learn in a data-driven fashion. To achieve this, we present the new method of interchange…

Causal approaches to post-hoc explainability for black-box prediction models (e.g., deep neural networks trained on image pixel data) have become increasingly popular. However, existing approaches have two important shortcomings: (i) the…

Predicting and enhancing inherent properties based on molecular structures is paramount to design tasks in medicine, materials science, and environmental management. Most of the current machine learning and deep learning approaches have…

Implicit Sentiment Analysis (ISA) aims to infer sentiment that is implied rather than explicitly stated, requiring models to perform deeper reasoning over subtle contextual cues. While recent prompting-based methods using Large Language…

This paper introduces the Impact-Driven AI Framework (IDAIF), a novel architectural methodology that integrates Theory of Change (ToC) principles with modern artificial intelligence system design. As AI systems increasingly influence…

Artificial Intelligence has achieved remarkable advancements in recent years, yet much of its progress relies on identifying increasingly complex correlations. Enabling causality awareness in AI has the potential to enhance its performance…

Causal inference is central to many areas of artificial intelligence, including complex reasoning, planning, knowledge-base construction, robotics, explanation, and fairness. An active community of researchers develops and enhances…

Causal decomposition analysis (CDA) is an approach for modeling the impact of hypothetical interventions to reduce disparities. It is useful for identifying foci that future interventions, including multilevel and multimodal interventions,…

We develop a new modeling framework for Inter-Subject Analysis (ISA). The goal of ISA is to explore the dependency structure between different subjects with the intra-subject dependency as nuisance. It has important applications in…

Evaluating the performance of heuristic optimisation algorithms is essential to determine how well they perform under various conditions. Recently, the BIAS toolbox was introduced as a behaviour benchmark to detect structural bias (SB) in…

Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However, existing methods often overfit to superficial cross-modal correlations, neglecting the…

Deep Research Agents (DRAs) aim to answer complex questions by searching the web, checking evidence, and synthesizing conclusions across heterogeneous sources. We introduce a category-theoretic framework for evaluating and improving such…

One of the several obstacles in the widespread use of AI systems is the lack of requirements of interpretability that can enable a layperson to ensure the safe and reliable behavior of such systems. We extend the analysis of an agent…

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…