Related papers: Interpreting and Controlling Model Behavior via Co…

Explaining black-box Artificial Intelligence (AI) models is a cornerstone for trustworthy AI and a prerequisite for its use in safety critical applications such that AI models can reliably assist humans in critical decisions. However,…

From a simple text prompt, generative-AI image models can create stunningly realistic and creative images bounded, it seems, by only our imagination. These models have achieved this remarkable feat thanks, in part, to the ingestion of…

Large Language Models such as GPTs (Generative Pre-trained Transformers) exhibit remarkable capabilities across a broad spectrum of applications. Nevertheless, due to their intrinsic complexity, these models present substantial challenges…

Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e.g., describing the image in a rough or detailed manner, in a factual or emotional…

Although psycholinguists and psychologists have long studied the tendency of linguistic strings to evoke mental images in hearers or readers, most computational studies have applied this concept of imageability only to isolated words. Using…

Human-centred systems require an understanding of human actions in the physical world. Temporally extended sequences of actions are intentional and structured, yet existing methods for recognising what actions are performed often do not…

Text-to-image generative models have achieved remarkable visual quality but still struggle with compositionality$-$accurately capturing object relationships, attribute bindings, and fine-grained details in prompts. A key limitation is that…

We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "meta-instructions" that control how models answer users'…

We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts that closely approximate neuron behavior. Compared to prior work that uses atomic labels as explanations, analyzing neurons…

As machine learning models are increasingly deployed in safety-critical domains, visual explanation techniques have become essential tools for supporting transparency. In this work, we reveal a new class of attacks that compromise model…

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions,…

In robot learning, it is common to either ignore the environment semantics, focusing on tasks like whole-body control which only require reasoning about robot-environment contacts, or conversely to ignore contact dynamics, focusing on…

Artificial intelligence (AI) is currently based largely on black-box machine learning models which lack interpretability. The field of eXplainable AI (XAI) strives to address this major concern, being critical in high-stakes areas such as…

Diverse and extensive work has recently been conducted on text-conditioned human motion generation. However, progress in the reverse direction, motion captioning, has seen less comparable advancement. In this paper, we introduce a novel…

There has been considerable recent interest in interpretable concept-based models such as Concept Bottleneck Models (CBMs), which first predict human-interpretable concepts and then map them to output classes. To reduce reliance on…

Concept-based interpretability methods offer a lens into the internals of foundation models by decomposing their embeddings into high-level concepts. These concept representations are most useful when they are compositional, meaning that…

This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act. Our main contributions are a new paradigm for estimating such models using a minimal query interface…

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…

Model interpretation, or explanation of a machine learning classifier, aims to extract generalizable knowledge from a trained classifier into a human-understandable format, for various purposes such as model assessment, debugging and trust.…