Related papers: Relational Local Explanations
Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts. Recent model agnostic methods address this problem by providing post-hoc interpretability methods by…
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…
Deep learning methods achieve remarkable predictive performance in modeling complex, large-scale data. However, assessing the quality of derived models has become increasingly challenging, as more classical statistical assumptions may no…
Interpretability has become a necessary feature for machine learning models deployed in critical scenarios, e.g. legal system, healthcare. In these situations, algorithmic decisions may have (potentially negative) long-lasting effects on…
This paper introduces an algorithm for discovering implicit and delayed causal relations between events observed by a robot at arbitrary times, with the objective of improving data-efficiency and interpretability of model-based…
Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally…
In many scientific problems such as video surveillance, modern genomics, and finance, data are often collected from diverse measurements across time that exhibit time-dependent heterogeneous properties. Thus, it is important to not only…
Feature attribution explains neural network outputs by identifying relevant input features. The attribution has to be faithful, meaning that the attributed features must mirror the input features that influence the output. One recent trend…
Machine learning (ML) models are becoming increasingly common in the atmospheric science community with a wide range of applications. To enable users to understand what an ML model has learned, ML explainability has become a field of active…
As machine learning models are increasingly deployed in high-stakes domains such as legal and financial decision-making, there has been growing interest in post-hoc methods for generating counterfactual explanations. Such explanations…
Explainability is needed to establish confidence in machine learning results. Some explainable methods take a post hoc approach to explain the weights of machine learning models, others highlight areas of the input contributing to…
Several explainable AI methods allow a Machine Learning user to get insights on the classification process of a black-box model in the form of local linear explanations. With such information, the user can judge which features are locally…
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of…
Many real-world planning domains involve diverse information sources, external entities, and variable-reliability agents, all of which may impact the confidence, risk, and sensitivity of plans. Humans reviewing a plan may lack context about…
Existing local model-agnostic explanation techniques are ineffective for machine learning models that consider inputs of variable lengths, as they do not consider temporal information embedded in these models. To address this limitation, we…
Decomposing a deep neural network's learned representations into interpretable features could greatly enhance its safety and reliability. To better understand features, we adopt a geometric perspective, viewing them as a learned coordinate…
Interpretability is essential for machine learning algorithms in high-stakes application fields such as medical image analysis. However, high-performing black-box neural networks do not provide explanations for their predictions, which can…
Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…
Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models,…
Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…