Aligning Generalisation Between Humans and Machines

Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and decision support but may also disrupt democracies and target individuals. The responsible use of AI increasingly shows the need for human-AI teaming, necessitating effective interaction between humans and machines. A crucial yet often overlooked aspect of these interactions is the different ways in which humans and machines generalise. In cognitive science, human generalisation commonly involves abstraction and concept learning. In contrast, AI generalisation encompasses out-of-domain generalisation in machine learning, rule-based reasoning in symbolic AI, and abstraction in neuro-symbolic AI. In this perspective paper, we combine insights from AI and cognitive science to identify key commonalities and differences across three dimensions: notions of generalisation, methods for generalisation, and evaluation of generalisation. We map the different conceptualisations of generalisation in AI and cognitive science along these three dimensions and consider their role in human-AI teaming. This results in interdisciplinary challenges across AI and cognitive science that must be tackled to provide a foundation for effective and cognitively supported alignment in human-AI teaming scenarios.

Knowledge Graph Enhanced Retrieval-Augmented Generation for Failure Mode and Effects Analysis

Failure mode and effects analysis (FMEA) is a critical tool for mitigating potential failures, particular during ramp-up phases of new products. However, its effectiveness is often limited by the missing reasoning capabilities of the FMEA tools, which are usually tabular structured. Meanwhile, large language models (LLMs) offer novel prospects for fine-tuning on custom datasets for reasoning within FMEA contexts. However, LLMs face challenges in tasks that require factual knowledge, a gap that retrieval-augmented generation (RAG) approaches aim to fill. RAG retrieves information from a non-parametric data store and uses a language model to generate responses. Building on this idea, we propose to advance the non-parametric data store with a knowledge graph (KG). By enhancing the RAG framework with a KG, our objective is to leverage analytical and semantic question-answering capabilities on FMEA data. This paper contributes by presenting a new ontology for FMEA observations, an algorithm for creating vector embeddings from the FMEA KG, and a KG enhanced RAG framework. Our approach is validated through a human study and we measure the performance of the context retrieval recall and precision.

CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations

Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at the same time, realistic features, positioning them well for generating counterfactual explanations for computer vision models. Answering "what if" questions of what needs to change to make an image classifier change its prediction, counterfactual explanations align well with human understanding and consequently help in making model behavior more comprehensible. Current methods succeed in generating authentic counterfactuals, but lack transparency as feature changes are not directly perceivable. To address this limitation, we introduce Concept-guided Latent Diffusion Counterfactual Explanations (CoLa-DCE). CoLa-DCE generates concept-guided counterfactuals for any classifier with a high degree of control regarding concept selection and spatial conditioning. The counterfactuals comprise an increased granularity through minimal feature changes. The reference feature visualization ensures better comprehensibility, while the feature localization provides increased transparency of "where" changed "what". We demonstrate the advantages of our approach in minimality and comprehensibility across multiple image classification models and datasets and provide insights into how our CoLa-DCE explanations help comprehend model errors like misclassification cases.

Locally Testing Model Detections for Semantic Global Concepts

Ensuring the quality of black-box Deep Neural Networks (DNNs) has become ever more significant, especially in safety-critical domains such as automated driving. While global concept encodings generally enable a user to test a model for a specific concept, linking global concept encodings to the local processing of single network inputs reveals their strengths and limitations. Our proposed framework global-to-local Concept Attribution (glCA) uses approaches from local (why a specific prediction originates) and global (how a model works generally) eXplainable Artificial Intelligence (xAI) to test DNNs for a predefined semantical concept locally. The approach allows for conditioning local, post-hoc explanations on predefined semantic concepts encoded as linear directions in the model's latent space. Pixel-exact scoring concerning the global concept usage assists the tester in further understanding the model processing of single data points for the selected concept. Our approach has the advantage of fully covering the model-internal encoding of the semantic concept and allowing the localization of relevant concept-related information. The results show major differences in the local perception and usage of individual global concept encodings and demand for further investigations regarding obtaining thorough semantic concept encodings.

When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX

Explanations for Convolutional Neural Networks (CNNs) based on relevance of input pixels might be too unspecific to evaluate which and how input features impact model decisions. Especially in complex real-world domains like biomedicine, the presence of specific concepts (e.g., a certain type of cell) and of relations between concepts (e.g., one cell type is next to another) might be discriminative between classes (e.g., different types of tissue). Pixel relevance is not expressive enough to convey this type of information. In consequence, model evaluation is limited and relevant aspects present in the data and influencing the model decisions might be overlooked. This work presents a novel method to explain and evaluate CNN models, which uses a concept- and relation-based explainer (CoReX). It explains the predictive behavior of a model on a set of images by masking (ir-)relevant concepts from the decision-making process and by constraining relations in a learned interpretable surrogate model. We test our approach with several image data sets and CNN architectures. Results show that CoReX explanations are faithful to the CNN model in terms of predictive outcomes. We further demonstrate that CoReX is a suitable tool for evaluating CNNs supporting identification and re-classification of incorrect or ambiguous classifications.

Can humans teach machines to code?

The goal of inductive program synthesis is for a machine to automatically generate a program from user-supplied examples of the desired behaviour of the program. A key underlying assumption is that humans can provide examples of sufficient quality to teach a concept to a machine. However, as far as we are aware, this assumption lacks both empirical and theoretical support. To address this limitation, we explore the question `Can humans teach machines to code?'. To answer this question, we conduct a study where we ask humans to generate examples for six programming tasks, such as finding the maximum element of a list. We compare the performance of a program synthesis system trained on (i) human-provided examples, (ii) randomly sampled examples, and (iii) expert-provided examples. Our results show that, on most of the tasks, non-expert participants did not provide sufficient examples for a program synthesis system to learn an accurate program. Our results also show that non-experts need to provide more examples than both randomly sampled and expert-provided examples.

Comprehensible Artificial Intelligence on Knowledge Graphs: A survey

Artificial Intelligence applications gradually move outside the safe walls of research labs and invade our daily lives. This is also true for Machine Learning methods on Knowledge Graphs, which has led to a steady increase in their application since the beginning of the 21st century. However, in many applications, users require an explanation of the Artificial Intelligences decision. This led to increased demand for Comprehensible Artificial Intelligence. Knowledge Graphs epitomize fertile soil for Comprehensible Artificial Intelligence, due to their ability to display connected data, i.e. knowledge, in a human- as well as machine-readable way. This survey gives a short history to Comprehensible Artificial Intelligence on Knowledge Graphs. Furthermore, we contribute by arguing that the concept Explainable Artificial Intelligence is overloaded and overlapping with Interpretable Machine Learning. By introducing the parent concept Comprehensible Artificial Intelligence, we provide a clear-cut distinction of both concepts while accounting for their similarities. Thus, we provide in this survey a case for Comprehensible Artificial Intelligence on Knowledge Graphs consisting of Interpretable Machine Learning on Knowledge Graphs and Explainable Artificial Intelligence on Knowledge Graphs. This leads to the introduction of a novel taxonomy for Comprehensible Artificial Intelligence on Knowledge Graphs. In addition, a comprehensive overview of the research on Comprehensible Artificial Intelligence on Knowledge Graphs is presented and put into the context of the taxonomy. Finally, research gaps in the field of Comprehensible Artificial Intelligence on Knowledge Graphs are identified for future research.

Explaining with Attribute-based and Relational Near Misses: An Interpretable Approach to Distinguishing Facial Expressions of Pain and Disgust

Explaining concepts by contrasting examples is an efficient and convenient way of giving insights into the reasons behind a classification decision. This is of particular interest in decision-critical domains, such as medical diagnostics. One particular challenging use case is to distinguish facial expressions of pain and other states, such as disgust, due to high similarity of manifestation. In this paper, we present an approach for generating contrastive explanations to explain facial expressions of pain and disgust shown in video sequences. We implement and compare two approaches for contrastive explanation generation. The first approach explains a specific pain instance in contrast to the most similar disgust instance(s) based on the occurrence of facial expressions (attributes). The second approach takes into account which temporal relations hold between intervals of facial expressions within a sequence (relations). The input to our explanation generation approach is the output of an interpretable rule-based classifier for pain and disgust.We utilize two different similarity metrics to determine near misses and far misses as contrasting instances. Our results show that near miss explanations are shorter than far miss explanations, independent from the applied similarity metric. The outcome of our evaluation indicates that pain and disgust can be distinguished with the help of temporal relations. We currently plan experiments to evaluate how the explanations help in teaching concepts and how they could be enhanced by further modalities and interaction.

Task Planning Support for Arborists and Foresters: Comparing Deep Learning Approaches for Tree Inventory and Tree Vitality Assessment Based on UAV-Data

Climate crisis and correlating prolonged, more intense periods of drought threaten tree health in cities and forests. In consequence, arborists and foresters suffer from increasing workloads and, in the best case, a consistent but often declining workforce. To optimise workflows and increase productivity, we propose a novel open-source end-to-end approach that generates helpful information and improves task planning of those who care for trees in and around cities. Our approach is based on RGB and multispectral UAV data, which is used to create tree inventories of city parks and forests and to deduce tree vitality assessments through statistical indices and Deep Learning. Due to EU restrictions regarding flying drones in urban areas, we will also use multispectral satellite data and fifteen soil moisture sensors to extend our tree vitality-related basis of data. Furthermore, Bamberg already has a georeferenced tree cadastre of around 15,000 solitary trees in the city area, which is also used to generate helpful information. All mentioned data is then joined and visualised in an interactive web application allowing arborists and foresters to generate individual and flexible evaluations, thereby improving daily task planning.

Explaining Hate Speech Classification with Model Agnostic Methods

There have been remarkable breakthroughs in Machine Learning and Artificial Intelligence, notably in the areas of Natural Language Processing and Deep Learning. Additionally, hate speech detection in dialogues has been gaining popularity among Natural Language Processing researchers with the increased use of social media. However, as evidenced by the recent trends, the need for the dimensions of explainability and interpretability in AI models has been deeply realised. Taking note of the factors above, the research goal of this paper is to bridge the gap between hate speech prediction and the explanations generated by the system to support its decision. This has been achieved by first predicting the classification of a text and then providing a posthoc, model agnostic and surrogate interpretability approach for explainability and to prevent model bias. The bidirectional transformer model BERT has been used for prediction because of its state of the art efficiency over other Machine Learning models. The model agnostic algorithm LIME generates explanations for the output of a trained classifier and predicts the features that influence the model decision. The predictions generated from the model were evaluated manually, and after thorough evaluation, we observed that the model performs efficiently in predicting and explaining its prediction. Lastly, we suggest further directions for the expansion of the provided research work.