Research Papers

fmeval is an open source library to evaluate large language models (LLMs) in a range of tasks. It helps practitioners evaluate their model for task performance and along multiple responsible AI dimensions. This paper presents the library and exposes its underlying design principles: simplicity, coverage, extensibility and performance. We then present how these were implemented in the scientific and engineering choices taken when developing fmeval. A case study demonstrates a typical use case for the library: picking a suitable model for a question answering task. We close by discussing limitations and further work in the development of the library. fmeval can be found at https://github.com/aws/fmeval.

Convolutional Neural Networks (CNNs) are known for their ability to learn hierarchical structures, naturally developing detectors for objects, and semantic concepts within their deeper layers. Activation maps (AMs) reveal these saliency regions, which are crucial for many Explainable AI (XAI) methods. However, the direct exploitation of raw AMs in CNNs for feature attribution remains underexplored in literature. This work revises Class Activation Map (CAM) methods by introducing the Label-free Activation Map (LaFAM), a streamlined approach utilizing raw AMs for feature attribution without reliance on labels. LaFAM presents an efficient alternative to conventional CAM methods, demonstrating particular effectiveness in saliency map generation for self-supervised learning while maintaining applicability in supervised learning scenarios.

The POST-Agents Proposal (PAP) is an idea for ensuring that advanced artificial agents never resist shutdown. A key part of the PAP is using a novel `Discounted Reward for Same-Length Trajectories (DReST)' reward function to train agents to (1) pursue goals effectively conditional on each trajectory-length (be `USEFUL'), and (2) choose stochastically between different trajectory-lengths (be `NEUTRAL' about trajectory-lengths). In this paper, we propose evaluation metrics for USEFULNESS and NEUTRALITY. We use a DReST reward function to train simple agents to navigate gridworlds, and we find that these agents learn to be USEFUL and NEUTRAL. Our results thus provide some initial evidence that DReST reward functions could train advanced agents to be USEFUL and NEUTRAL. Our theoretical work suggests that these agents would be useful and shutdownable.

The interpretability of machine learning models has gained increasing attention, particularly in scientific domains where high precision and accountability are crucial. This research focuses on distinguishing between two critical data patterns -- sensitive patterns (model-related) and decisive patterns (task-related) -- which are commonly used as model interpretations but often lead to confusion. Specifically, this study compares the effectiveness of two main streams of interpretation methods: post-hoc methods and self-interpretable methods, in detecting these patterns. Recently, geometric deep learning (GDL) has shown superior predictive performance in various scientific applications, creating an urgent need for principled interpretation methods. Therefore, we conduct our study using several representative GDL applications as case studies. We evaluate thirteen interpretation methods applied to three major GDL backbone models, using four scientific datasets to assess how well these methods identify sensitive and decisive patterns. Our findings indicate that post-hoc methods tend to provide interpretations better aligned with sensitive patterns, whereas certain self-interpretable methods exhibit strong and stable performance in detecting decisive patterns. Additionally, our study offers valuable insights into improving the reliability of these interpretation methods. For example, ensembling post-hoc interpretations from multiple models trained on the same task can effectively uncover the task's decisive patterns.

Explainable artificial intelligence (XAI) methods have been proposed to interpret model decisions in classification and, more recently, in semantic segmentation. However, instance-level XAI for semantic segmentation, namely explanations focused on a single object among multiple instances of the same class, remains largely unexplored. Such explanations are particularly important in multi-lesional diseases to understand what drives the detection and contouring of a specific lesion. We propose instance-level explanation maps for semantic segmentation by extending SmoothGrad and Grad-CAM++ to obtain quantitative instance saliency. These methods were applied to the segmentation of white matter lesions (WMLs), a magnetic resonance imaging biomarker in multiple sclerosis. We used 4023 FLAIR and MPRAGE MRI scans from 687 patients collected at the University Hospital of Basel, Switzerland, with WML masks annotated by four expert clinicians. Three deep learning architectures, a 3D U-Net, nnU-Net, and Swin UNETR, were trained and evaluated, achieving normalized Dice scores of 0.71, 0.78, and 0.80, respectively. Instance saliency maps showed that the models relied primarily on FLAIR rather than MPRAGE for WML segmentation, with positive saliency inside lesions and negative saliency in their immediate neighborhood, consistent with clinical practice. Peak saliency values differed significantly across correct and incorrect predictions, suggesting that quantitative instance saliency may help identify segmentation errors. In conclusion, we introduce two architecture-agnostic XAI methods that provide quantitative instance-level explanations for semantic segmentation and support clinically meaningful interpretation of model decisions.

Unified Explanations in Machine Learning Models: A Perturbation Approach

Jacob Dineen, Don Kridel, Daniel Dolk +1

A high-velocity paradigm shift towards Explainable Artificial Intelligence (XAI) has emerged in recent years. Highly complex Machine Learning (ML) models have flourished in many tasks of intelligence, and the questions have started to shift away from traditional metrics of validity towards something deeper: What is this model telling me about my data, and how is it arriving at these conclusions? Inconsistencies between XAI and modeling techniques can have the undesirable effect of casting doubt upon the efficacy of these explainability approaches. To address these problems, we propose a systematic, perturbation-based analysis against a popular, model-agnostic method in XAI, SHapley Additive exPlanations (Shap). We devise algorithms to generate relative feature importance in settings of dynamic inference amongst a suite of popular machine learning and deep learning methods, and metrics that allow us to quantify how well explanations generated under the static case hold. We propose a taxonomy for feature importance methodology, measure alignment, and observe quantifiable similarity amongst explanation models across several datasets.

As the number of dementia patients rises, the need for accurate diagnostic procedures rises as well. Current methods, like using an MRI scan, rely on human input, which can be inaccurate. However, the decision logic behind machine learning algorithms and their outputs cannot be explained, as most operate in black-box models. Therefore, to increase the accuracy of diagnosing dementia through MRIs, a convolution neural network has been developed and trained using an open-source database of 6400 MRI scans divided into 4 dementia classes. The model, which attained a 98 percent validation accuracy, was shown to be well fit and able to generalize to new data. Furthermore, to aid in the visualization of the model output, an explainable AI algorithm was developed by visualizing the outputs of individual filters in each convolution layer, which highlighted regions of interest in the scan. These outputs do a great job of identifying the image features that contribute most to the model classification, thus allowing users to visualize and understand the results. Altogether, this combination of the convolution neural network and explainable AI algorithm creates a system that can be used in the medical field to not only aid in the proper classification of dementia but also allow everyone involved to visualize and understand the results.

Expert search and team formation systems operate on collaboration networks, with nodes representing individuals, labeled with their skills, and edges denoting collaboration relationships. Given a keyword query corresponding to the desired skills, these systems identify experts that best match the query. However, state-of-the-art solutions to this problem lack transparency. To address this issue, we propose ExES, a tool designed to explain expert search and team formation systems using factual and counterfactual methods from the field of explainable artificial intelligence (XAI). ExES uses factual explanations to highlight important skills and collaborations, and counterfactual explanations to suggest new skills and collaborations to increase the likelihood of being identified as an expert. Towards a practical deployment as an interactive explanation tool, we present and experimentally evaluate a suite of pruning strategies to speed up the explanation search. In many cases, our pruning strategies make ExES an order of magnitude faster than exhaustive search, while still producing concise and actionable explanations.

The evolving landscape of explainable artificial intelligence (XAI) aims to improve the interpretability of intricate machine learning (ML) models, yet faces challenges in formalisation and empirical validation, being an inherently unsupervised process. In this paper, we bring together various benchmark datasets and novel performance metrics in an initial benchmarking platform, the Explainable AI Comparison Toolkit (EXACT), providing a standardised foundation for evaluating XAI methods. Our datasets incorporate ground truth explanations for class-conditional features, and leveraging novel quantitative metrics, this platform assesses the performance of post-hoc XAI methods in the quality of the explanations they produce. Our recent findings have highlighted the limitations of popular XAI methods, as they often struggle to surpass random baselines, attributing significance to irrelevant features. Moreover, we show the variability in explanations derived from different equally performing model architectures. This initial benchmarking platform therefore aims to allow XAI researchers to test and assure the high quality of their newly developed methods.

Stock Market Dynamics Through Deep Learning Context

Amirhossein Aminimehr, Amin Aminimehr, Hamid Moradi Kamali +2

Studies conducted on financial market prediction lack a comprehensive feature set that can carry a broad range of contributing factors; therefore, leading to imprecise results. Furthermore, while cooperating with the most recent innovations in explainable AI, studies have not provided an illustrative summary of market-driving factors using this powerful tool. Therefore, in this study, we propose a novel feature matrix that holds a broad range of features including Twitter content and market historical data to perform a binary classification task of one step ahead prediction. The utilization of our proposed feature matrix not only leads to improved prediction accuracy when compared to existing feature representations, but also its combination with explainable AI allows us to introduce a fresh analysis approach regarding the importance of the market-driving factors included. Thanks to the Lime interpretation technique, our interpretation study shows that the volume of tweets is the most important factor included in our feature matrix that drives the market's movements.

The necessity for interpretability in natural language processing (NLP) has risen alongside the growing prominence of large language models. Among the myriad tasks within NLP, text generation stands out as a primary objective of autoregressive models. The NLP community has begun to take a keen interest in gaining a deeper understanding of text generation, leading to the development of model-agnostic explainable artificial intelligence (xAI) methods tailored to this task. The design and evaluation of explainability methods are non-trivial since they depend on many factors involved in the text generation process, e.g., the autoregressive model and its stochastic nature. This paper outlines 17 challenges categorized into three groups that arise during the development and assessment of attribution-based explainability methods. These challenges encompass issues concerning tokenization, defining explanation similarity, determining token importance and prediction change metrics, the level of human intervention required, and the creation of suitable test datasets. The paper illustrates how these challenges can be intertwined, showcasing new opportunities for the community. These include developing probabilistic word-level explainability methods and engaging humans in the explainability pipeline, from the data design to the final evaluation, to draw robust conclusions on xAI methods.

In this paper, we address two critical challenges in the domain of flood detection: the computational expense of large-scale time series change detection and the lack of interpretable decision-making processes on explainable AI (XAI). To overcome these challenges, we proposed an interpretable multi-stage approach to flood detection, IMAFD has been proposed. It provides an automatic, efficient and interpretable solution suitable for large-scale remote sensing tasks and offers insight into the decision-making process. The proposed IMAFD approach combines the analysis of the dynamic time series image sequences to identify images with possible flooding with the static, within-image semantic segmentation. It combines anomaly detection (at both image and pixel level) with semantic segmentation. The flood detection problem is addressed through four stages: (1) at a sequence level: identifying the suspected images (2) at a multi-image level: detecting change within suspected images (3) at an image level: semantic segmentation of images into Land, Water or Cloud class (4) decision making. Our contributions are two folder. First, we efficiently reduced the number of frames to be processed for dense change detection by providing a multi-stage holistic approach to flood detection. Second, the proposed semantic change detection method (stage 3) provides human users with an interpretable decision-making process, while most of the explainable AI (XAI) methods provide post hoc explanations. The evaluation of the proposed IMAFD framework was performed on three datasets, WorldFloods, RavAEn and MediaEval. For all the above datasets, the proposed framework demonstrates a competitive performance compared to other methods offering also interpretability and insight.