Related papers: Using Counterexample Generation and Theory Explora…

There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…

Existing adversarial example research focuses on digitally inserted perturbations on top of existing natural image datasets. This construction of adversarial examples is not realistic because it may be difficult, or even impossible, for an…

Real-life tasks such as giving legal or technical advice often lack complete context at the outset and can have disparate answers depending thereon. The ability to derive missing factual information by asking clarifying questions (ACQ) is…

Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail approval, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they…

This work presents code to procedurally generate examples for the ARC training tasks. For each of the 400 tasks, an example generator following the transformation logic of the original examples was created. In effect, the assumed underlying…

While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only instantiate limited types of perturbations such as…

Contrastive learning (CL), a self-supervised learning approach, can effectively learn visual representations from unlabeled data. Given the CL training data, generative models can be trained to generate synthetic data to supplement the real…

Recent advancements in transformer-based models have greatly improved the ability of Question Answering (QA) systems to provide correct answers; in particular, answer sentence selection (AS2) models, core components of retrieval-based…

Contrastive learning is an efficient approach to self-supervised representation learning. Although recent studies have made progress in the theoretical understanding of contrastive learning, the investigation of how to characterize the…

Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation method -- how…

Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive RAG enhances this approach by enabling dynamic retrieval…

Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems. In computer vision applications, generative counterfactual…

Explanations are an important tool for gaining insights into the behavior of ML models, calibrating user trust and ensuring regulatory compliance. Past few years have seen a flurry of post-hoc methods for generating model explanations, many…

Large Language Models (LLMs), despite achieving state-of-the-art results in a number of evaluation tasks, struggle to maintain their performance when logical reasoning is strictly required to correctly infer a prediction. In this work, we…

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…

Large Language Models (LLMs) have shown promising results in automating formal verification. However, existing approaches treat proof generation as a static, end-to-end prediction over source code, relying on limited verifier feedback and…

Clustering algorithms rely on complex optimisation processes that may be difficult to comprehend, especially for individuals who lack technical expertise. While many explainable artificial intelligence techniques exist for supervised…

Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom address the issue of predictive uncertainty, i.e., how likely it…

The last decade has witnessed the proliferation of Deep Learning models in many applications, achieving unrivaled levels of predictive performance. Unfortunately, the black-box nature of Deep Learning models has posed unanswered questions…

Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill user instructions. Existing approaches, such as…