Related papers: Interpretability at Scale: Identifying Causal Mech…

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…

Large Language Models (LLMs) have demonstrated remarkable progress in instruction following and general-purpose reasoning. However, achieving high-quality alignment with human intent and safety norms without human annotations remains a…

Deep Neural Networks (DNNs) are extremely computationally demanding, which presents a large barrier to their deployment on resource-constrained devices. Since such devices are where many emerging deep learning applications lie (e.g.,…

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets,…

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…

Practical use of neural networks often involves requirements on latency, energy and memory among others. A popular approach to find networks under such requirements is through constrained Neural Architecture Search (NAS). However, previous…

Distributed acoustic sensing (DAS) technology represents an innovative fiber-optic-based sensing methodology that enables real-time acoustic signal monitoring through the detection of minute perturbations along optical fibers. This sensing…

We present dPASP, a novel declarative probabilistic logic programming framework for differentiable neuro-symbolic reasoning. The framework allows for the specification of discrete probabilistic models with neural predicates, logic…

Causal discovery amounts to unearthing causal relationships amongst features in data. It is a crucial companion to causal inference, necessary to build scientific knowledge without resorting to expensive or impossible randomised control…

Causal decomposition analysis (CDA) is an approach for modeling the impact of hypothetical interventions to reduce disparities. It is useful for identifying foci that future interventions, including multilevel and multimodal interventions,…

Causal discovery (CD) plays a pivotal role in numerous scientific fields by clarifying the causal relationships that underlie phenomena observed in diverse disciplines. Despite significant advancements in CD algorithms that enhance bias and…

In recent years, machine learning models have been increasingly applied to spectroscopic datasets for chemical and biomedical analysis. For their successful adoption, particularly in clinical and safety-critical settings, professionals and…

This paper addresses the issue of implicit stereotypes that may arise during the generation process of large language models. It proposes an interpretable bias detection method aimed at identifying hidden social biases in model outputs,…

Moving loads such as cars and trains are very useful sources of seismic waves, which can be analyzed to retrieve information on the seismic velocity of subsurface materials using the techniques of ambient noise seismology. This information…

A desirable property of interpretable models is small size, so that they are easily understandable by humans. This leads to the following challenges: (a) small sizes typically imply diminished accuracy, and (b) bespoke levers provided by…

Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverage large language models (LLMs) at increasing levels of…

This dissertation addresses achieving causal interpretability in Deep Learning for Software Engineering (DL4SE). While Neural Code Models (NCMs) show strong performance in automating software tasks, their lack of transparency in causal…

Learning an explainable classifier often results in low accuracy model or ends up with a huge rule set, while learning a deep model is usually more capable of handling noisy data at scale, but with the cost of hard to explain the result and…

As agents based on large language models are increasingly deployed to long-horizon tasks, maintaining their alignment with stakeholder preferences becomes critical. Effective alignment in such settings requires reward models that are…

Structural causal models (SCMs) allow us to investigate complex systems at multiple levels of resolution. The causal abstraction (CA) framework formalizes the mapping between high- and low-level SCMs. We address CA learning in a challenging…