Related papers: Are We Merely Justifying Results ex Post Facto? Qu…

The overarching goal of Explainable AI is to develop systems that not only exhibit intelligent behaviours, but also are able to explain their rationale and reveal insights. In explainable machine learning, methods that produce a high level…

Reinforcement Learning from Human Feedback (RLHF) has proven effective in aligning large language models with human intentions, yet it often relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive…

Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Post-hoc interpretability, which provides…

Existing and planned legislation stipulates various obligations to provide information about machine learning algorithms and their functioning, often interpreted as obligations to "explain". Many researchers suggest using post-hoc…

It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…

Large language models (LLMs) are increasingly used for long-document question answering, where reliable attribution to sources is critical for trust. Existing post-hoc attribution methods work well for extractive QA but struggle in…

Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by…

The majority of existing post-hoc explanation approaches for machine learning models produce independent, per-variable feature attribution scores, ignoring a critical inherent characteristics of homogeneously structured data, such as visual…

As the applications of Natural Language Processing (NLP) in sensitive areas like Political Profiling, Review of Essays in Education, etc. proliferate, there is a great need for increasing transparency in NLP models to build trust with…

Existing explanation methods for image classification struggle to provide faithful and plausible explanations. This paper addresses this issue by proposing a post-hoc natural language explanation method that can be applied to any CNN-based…

The performance of Video Question Answering (VideoQA) models is fundamentally constrained by the nature of their supervision, which typically consists of isolated, factual question-answer pairs. This "bag-of-facts" approach fails to capture…

Concurrent to the rapid progress in the development of neural-network based models in areas like natural language processing and computer vision, the need for creating explanations for the predictions of these black-box models has risen…

The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information. We apply a reinforcement learning framework which…

While Large Language Models (LLMs) have found success in real-world applications, their underlying explanatory process is still poorly understood. This paper proposes IBE-Eval, a framework inspired by philosophical accounts on Inference to…

This paper presents a formal approach to explaining change of inference in Quantitative Bipolar Argumentation Frameworks (QBAFs). When drawing conclusions from a QBAF and updating the QBAF to then again draw conclusions (and so on), our…

Despite the rapid progress in multihop question-answering (QA), models still have trouble explaining why an answer is correct, with limited explanation training data available to learn from. To address this, we introduce three explanation…

Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…

Artificial Intelligence (AI) is often an integral part of modern decision support systems. The best-performing predictive models used in AI-based decision support systems lack transparency. Explainable Artificial Intelligence (XAI) aims to…

We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the…

Even as we engineer LLMs for alignment and safety, they often uncover biases from pre-training data's statistical regularities (from disproportionate co-occurrences to stereotypical associations mirroring human cognitive biases). This leads…