相关论文: Evaluating Attribution Methods using White-Box LST…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

In some situations, the interpretability of the machine learning models plays a role as important as the model accuracy. Interpretability comes from the need to trust the prediction model, verify some of its properties, or even enforce them…

Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies,…

As artificial intelligence is increasingly affecting all parts of society and life, there is growing recognition that human interpretability of machine learning models is important. It is often argued that accuracy or other similar…

Post-hoc interpretability methods are critical tools to explain neural-network results. Several post-hoc methods have emerged in recent years, but when applied to a given task, they produce different results, raising the question of which…

In recent years, a number of artificial intelligent services have been developed such as defect detection system or diagnosis system for customer services. Unfortunately, the core in these services is a black-box in which human cannot…

Recent efforts to learn reward functions from human feedback have tended to use deep neural networks, whose lack of transparency hampers our ability to explain agent behaviour or verify alignment. We explore the merits of learning…

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…

Computationally explicit hypotheses of brain function derived from machine learning (ML)-based models have recently revolutionized neuroscience. Despite the unprecedented ability of these artificial neural networks (ANNs) to capture…

Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their…

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…

Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impact, raising questions about its relevance and utility. This…

The use of sophisticated machine learning models for critical decision making is faced with a challenge that these models are often applied as a "black-box". This has led to an increased interest in interpretable machine learning, where…

Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks. However, a long-standing criticism against neural network models is the lack of interpretability, which not only…

Data attribution methods quantify the influence of training data on model outputs and are becoming increasingly relevant for a wide range of LLM research and applications, including dataset curation, model interpretability, data valuation.…

The ubiquity of neural networks (NNs) in real-world applications, from healthcare to natural language processing, underscores their immense utility in capturing complex relationships within high-dimensional data. However, NNs come with…

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…

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…

Instruction-tuned LLMs are able to provide \textit{an} explanation about their output to users by generating self-explanations, without requiring the application of complex interpretability techniques. In this paper, we analyse whether this…

With the long term accumulation of high quality educational data, artificial intelligence has shown excellent performance in knowledge tracing. However, due to the lack of interpretability and transparency of some algorithms, this approach…