Large language models (LLMs) are widely deployed in various downstream tasks, e.g., auto-completion, aided writing, or chat-based text generation. However, the considered output candidates of the underlying search algorithm are under-explored and under-explained. We tackle this shortcoming by proposing a tree-in-the-loop approach, where a visual representation of the beam search tree is the central component for analyzing, explaining, and adapting the generated outputs. To support these tasks, we present generAItor, a visual analytics technique, augmenting the central beam search tree with various task-specific widgets, providing targeted visualizations and interaction possibilities. Our approach allows interactions on multiple levels and offers an iterative pipeline that encompasses generating, exploring, and comparing output candidates, as well as fine-tuning the model based on adapted data. Our case study shows that our tool generates new insights in gender bias analysis beyond state-of-the-art template-based methods. Additionally, we demonstrate the applicability of our approach in a qualitative user study. Finally, we quantitatively evaluate the adaptability of the model to few samples, as occurring in text-generation use cases.
The growing popularity of generative language models has amplified interest in interactive methods to guide model outputs. Prompt refinement is considered one of the most effective means to influence output among these methods. We identify several challenges associated with prompting large language models, categorized into data- and model-specific, linguistic, and socio-linguistic challenges. A comprehensive examination of model outputs, including runner-up candidates and their corresponding probabilities, is needed to address these issues. The beam search tree, the prevalent algorithm to sample model outputs, can inherently supply this information. Consequently, we introduce an interactive visual method for investigating the beam search tree, facilitating analysis of the decisions made by the model during generation. We quantitatively show the value of exposing the beam search tree and present five detailed analysis scenarios addressing the identified challenges. Our methodology validates existing results and offers additional insights.
Given the increasing amount and general complexity of time series data in domains such as finance, weather forecasting, and healthcare, there is a growing need for state-of-the-art performance models that can provide interpretable insights into underlying patterns and relationships. Attribution techniques enable the extraction of explanations from time series models to gain insights but are hard to evaluate for their robustness and trustworthiness. We propose the Attribution Stability Indicator (ASI), a measure to incorporate robustness and trustworthiness as properties of attribution techniques for time series into account. We extend a perturbation analysis with correlations of the original time series to the perturbed instance and the attributions to include wanted properties in the measure. We demonstrate the wanted properties based on an analysis of the attributions in a dimension-reduced space and the ASI scores distribution over three whole time series classification datasets.
With the rising necessity of explainable artificial intelligence (XAI), we see an increase in task-dependent XAI methods on varying abstraction levels. XAI techniques on a global level explain model behavior and on a local level explain sample predictions. We propose a visual analytics workflow to support seamless transitions between global and local explanations, focusing on attributions and counterfactuals on time series classification. In particular, we adapt local XAI techniques (attributions) that are developed for traditional datasets (images, text) to analyze time series classification, a data type that is typically less intelligible to humans. To generate a global overview, we apply local attribution methods to the data, creating explanations for the whole dataset. These explanations are projected onto two dimensions, depicting model behavior trends, strategies, and decision boundaries. To further inspect the model decision-making as well as potential data errors, a what-if analysis facilitates hypothesis generation and verification on both the global and local levels. We constantly collected and incorporated expert user feedback, as well as insights based on their domain knowledge, resulting in a tailored analysis workflow and system that tightly integrates time series transformations into explanations. Lastly, we present three use cases, verifying that our technique enables users to (1)~explore data transformations and feature relevance, (2)~identify model behavior and decision boundaries, as well as, (3)~the reason for misclassifications.
Explainable Artificial Intelligence (XAI) has gained significant attention recently as the demand for transparency and interpretability of machine learning models has increased. In particular, XAI for time series data has become increasingly important in finance, healthcare, and climate science. However, evaluating the quality of explanations, such as attributions provided by XAI techniques, remains challenging. This paper provides an in-depth analysis of using perturbations to evaluate attributions extracted from time series models. A perturbation analysis involves systematically modifying the input data and evaluating the impact on the attributions generated by the XAI method. We apply this approach to several state-of-the-art XAI techniques and evaluate their performance on three time series classification datasets. Our results demonstrate that the perturbation analysis approach can effectively evaluate the quality of attributions and provide insights into the strengths and limitations of XAI techniques. Such an approach can guide the selection of XAI methods for time series data, e.g., focusing on return time rather than precision, and facilitate the development of more reliable and interpretable machine learning models for time series analysis.
While deep reinforcement learning (RL) agents have showcased strong results across many domains, a major concern is their inherent opaqueness and the safety of such systems in real-world use cases. To overcome these issues, we need agents that can quantify their uncertainty and detect out-of-distribution (OOD) states. Existing uncertainty estimation techniques, like Monte-Carlo Dropout or Deep Ensembles, have not seen widespread adoption in on-policy deep RL. We posit that this is due to two reasons: concepts like uncertainty and OOD states are not well defined compared to supervised learning, especially for on-policy RL methods. Secondly, available implementations and comparative studies for uncertainty estimation methods in RL have been limited. To overcome the first gap, we propose definitions of uncertainty and OOD for Actor-Critic RL algorithms, namely, proximal policy optimization (PPO), and present possible applicable measures. In particular, we discuss the concepts of value and policy uncertainty. The second point is addressed by implementing different uncertainty estimation methods and comparing them across a number of environments. The OOD detection performance is evaluated via a custom evaluation benchmark of in-distribution (ID) and OOD states for various RL environments. We identify a trade-off between reward and OOD detection performance. To overcome this, we formulate a Pareto optimization problem in which we simultaneously optimize for reward and OOD detection performance. We show experimentally that the recently proposed method of Masksembles strikes a favourable balance among the survey methods, enabling high-quality uncertainty estimation and OOD detection while matching the performance of original RL agents.
Robustness to adversarial perturbations has been explored in many areas of computer vision. This robustness is particularly relevant in vision-based reinforcement learning, as the actions of autonomous agents might be safety-critic or impactful in the real world. We investigate the susceptibility of vision-based reinforcement learning agents to gradient-based adversarial attacks and evaluate a potential defense. We observe that Bottleneck Attention Modules (BAM) included in CNN architectures can act as potential tools to increase robustness against adversarial attacks. We show how learned attention maps can be used to recover activations of a convolutional layer by restricting the spatial activations to salient regions. Across a number of RL environments, BAM-enhanced architectures show increased robustness during inference. Finally, we discuss potential future research directions.
Neural networks grow vastly in size to tackle more sophisticated tasks. In many cases, such large networks are not deployable on particular hardware and need to be reduced in size. Pruning techniques help to shrink deep neural networks to smaller sizes by only decreasing their performance as little as possible. However, such pruning algorithms are often hard to understand by applying them and do not include domain knowledge which can potentially be bad for user goals. We propose ViNNPruner, a visual interactive pruning application that implements state-of-the-art pruning algorithms and the option for users to do manual pruning based on their knowledge. We show how the application facilitates gaining insights into automatic pruning algorithms and semi-automatically pruning oversized networks to make them more efficient using interactive visualizations.
Manually investigating sheet music collections is challenging for music analysts due to the magnitude and complexity of underlying features, structures, and contextual information. However, applying sophisticated algorithmic methods would require advanced technical expertise that analysts do not necessarily have. Bridging this gap, we contribute CorpusVis, an interactive visual workspace, enabling scalable and multi-faceted analysis. Our proposed visual analytics dashboard provides access to computational methods, generating varying perspectives on the same data. The proposed application uses metadata including composers, type, epoch, and low-level features, such as pitch, melody, and rhythm. To evaluate our approach, we conducted a pair analytics study with nine participants. The qualitative results show that CorpusVis supports users in performing exploratory and confirmatory analysis, leading them to new insights and findings. In addition, based on three exemplary workflows, we demonstrate how to apply our approach to different tasks, such as exploring musical features or comparing composers.
Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attributions for samples, for instance, on images. However, heatmaps are not always the ideal visualization to explain certain model decisions for other data types. In this review, we focus on attribution visualizations for time series. We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.