相关论文: Interpreting and Controlling Model Behavior via Co…

In the contemporary era of intelligent connectivity, Affective Computing (AC), which enables systems to recognize, interpret, and respond to human behavior states, has become an integrated part of many AI systems. As one of the most…

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-making in continuously evolving conditions. As such, correctness depends not only on the output of individual model calls, but also on how to…

Algorithmic approaches to interpreting machine learning models have proliferated in recent years. We carry out human subject tests that are the first of their kind to isolate the effect of algorithmic explanations on a key aspect of model…

Interpretability and explainability of neural networks is continuously increasing in importance, especially within safety-critical domains and to provide the social right to explanation. Concept based explanations align well with how humans…

Model interpretability and model editing are crucial goals in the age of large language models. Interestingly, there exists a link between these two goals: if a method is able to systematically edit model behavior with regard to a human…

In this paper we introduce a general estimation methodology for learning a model of human perception and control in a sensorimotor control task based upon a finite set of demonstrations. The model's structure consists of i the agent's…

The incredible generative ability of large-scale text-to-image (T2I) models has demonstrated strong power of learning complex structures and meaningful semantics. However, relying solely on text prompts cannot fully take advantage of the…

Large Language Models demonstrate remarkable mathematical capabilities but at the same time struggle with abstract reasoning and planning. In this study, we explore whether Transformers can learn to abstract and generalize the rules…

With the increasing adoption of predictive models trained using machine learning across a wide range of high-stakes applications, e.g., health care, security, criminal justice, finance, and education, there is a growing need for effective…

Controllable semantic image editing enables a user to change entire image attributes with a few clicks, e.g., gradually making a summer scene look like it was taken in winter. Classic approaches for this task use a Generative Adversarial…

We present a framework that allows users to incorporate the semantics of their domain knowledge for topic model refinement while remaining model-agnostic. Our approach enables users to (1) understand the semantic space of the model, (2)…

This thesis advances semantic representation learning to render language representations or models more semantically and geometrically interpretable, and to enable localised, quasi-symbolic, compositional control through deliberate shaping…

With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models. Although many supposedly interpretable models have been proposed,…

Most image captioning frameworks generate captions directly from images, learning a mapping from visual features to natural language. However, editing existing captions can be easier than generating new ones from scratch. Intuitively, when…

Recent works show that text-to-image generative models are surprisingly vulnerable to a variety of poisoning attacks. Empirical results find that these models can be corrupted by altering associations between individual text prompts and…

Concept Bottleneck Models (CBM) are inherently interpretable models that factor model decisions into human-readable concepts. They allow people to easily understand why a model is failing, a critical feature for high-stakes applications.…

As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…

Explaining the behavior of a black box machine learning model at the instance level is useful for building trust. However, it is also important to understand how the model behaves globally. Such an understanding provides insight into both…

Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at…