Related papers: Causal Proxy Models for Concept-Based Model Explan…

Causal inference is one of the most fundamental problems across all domains of science. We address the problem of inferring a causal direction from two observed discrete symbolic sequences $X$ and $Y$. We present a framework which relies on…

Causal reasoning is one of the primary bottlenecks that Large Language Models (LLMs) must overcome to attain human-level intelligence. Recent studies indicate that LLMs display near-random performance on reasoning tasks. To address this, we…

The core of the dialogue system is to generate relevant, informative, and human-like responses based on extensive dialogue history. Recently, dialogue generation domain has seen mainstream adoption of large language models (LLMs), due to…

Currently, there is a significant amount of research being conducted in the field of artificial intelligence to improve the explainability and interpretability of deep learning models. It is found that if end-users understand the reason for…

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…

Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?"), simulate changes in the situation to evaluate how this impacts…

This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reasoning abilities via precise fine-tuning. Despite LLMs' proficiency in diverse tasks, their…

Concepts benefit natural language understanding but are far from complete in existing knowledge graphs (KGs). Recently, pre-trained language models (PLMs) have been widely used in text-based concept extraction (CE). However, PLMs tend to…

Machine learning models that offer excellent predictive performance often lack the interpretability necessary to support integrated human machine decision-making. In clinical medicine and other high-risk settings, domain experts may be…

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

We propose a novel training regime termed counterfactual training that leverages counterfactual explanations to increase the explanatory capacity of models. Counterfactual explanations have emerged as a popular post-hoc explanation method…

One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one feature. Constructing such counterfactual poses specific challenges…

The principle of independent causal mechanisms (ICM) states that generative processes of real world data consist of independent modules which do not influence or inform each other. While this idea has led to fruitful developments in the…

Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions. For CEs to be useful, it is important that they are easy for users to interpret. Existing methods for…

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

Counterfactual reasoning has emerged as a crucial technique for generalizing the reasoning capabilities of large language models (LLMs). By generating and analyzing counterfactual scenarios, researchers can assess the adaptability and…

Deep Neural Networks (DNNs) are often considered black boxes due to their opaque decision-making processes. To reduce their opacity Concept Models (CMs), such as Concept Bottleneck Models (CBMs), were introduced to predict human-defined…

Interpretability research on large language models (LLMs) has yielded important insights into model behaviour, yet recurring pitfalls persist: findings that do not generalise, and causal interpretations that outrun the evidence. Our…

Conceptual modeling (CM) applies abstraction to reduce the complexity of a system under study (e.g., an excerpt of reality). As a result of the conceptual modeling process a human interpretable, formalized representation (i.e., a conceptual…

Causal Models are increasingly suggested as a means to reason about the behavior of cyber-physical systems in socio-technical contexts. They allow us to analyze courses of events and reason about possible alternatives. Until now, however,…