Artificial Intelligence (cs.AI)

Abstract: Improving the decision-making capabilities of agents is a key challenge on the road to artificial intelligence. To improve the planning skills needed to make good decisions, MuZero's agent combines prediction by a network model and planning by a tree search using the predictions. MuZero's learning process can fail when predictions are poor but planning requires them. We use this as an impetus to get the agent to explore parts of the decision tree in the environment that it otherwise would not explore. The agent achieves this, first by normal planning to come up with an improved policy. Second, it randomly deviates from this policy at the beginning of each training episode. And third, it switches back to the improved policy at a random time step to experience the rewards from the environment associated with the improved policy, which is the basis for learning the correct value expectation. The simple board game Tic-Tac-Toe is used to illustrate how this approach can improve the agent's decision-making ability. The source code, written entirely in Java, is available at https://github.com/enpasos/muzero.

Abstract: We study the multi-objective minimum weight base problem, an abstraction of classical NP-hard combinatorial problems such as the multi-objective minimum spanning tree problem. We prove some important properties of the convex hull of the non-dominated front, such as its approximation quality and an upper bound on the number of extreme points. Using these properties, we give the first run-time analysis of the MOEA/D algorithm for this problem, an evolutionary algorithm that effectively optimizes by decomposing the objectives into single-objective components. We show that the MOEA/D, given an appropriate decomposition setting, finds all extreme points within expected fixed-parameter polynomial time in the oracle model, the parameter being the number of objectives. Experiments are conducted on random bi-objective minimum spanning tree instances, and the results agree with our theoretical findings. Furthermore, compared with a previously studied evolutionary algorithm for the problem GSEMO, MOEA/D finds all extreme points much faster across all instances.

Abstract: Since the release of OpenAI's ChatGPT, generative language models have attracted extensive public attention. The increased usage has highlighted generative models' broad utility, but also revealed several forms of embedded bias. Some is induced by the pre-training corpus; but additional bias specific to generative models arises from the use of subjective fine-tuning to avoid generating harmful content. Fine-tuning bias may come from individual engineers and company policies, and affects which prompts the model chooses to refuse. In this experiment, we characterize ChatGPT's refusal behavior using a black-box attack. We first query ChatGPT with a variety of offensive and benign prompts (n=1,730), then manually label each response as compliance or refusal. Manual examination of responses reveals that refusal is not cleanly binary, and lies on a continuum; as such, we map several different kinds of responses to a binary of compliance or refusal. The small manually-labeled dataset is used to train a refusal classifier, which achieves an accuracy of 92%. Second, we use this refusal classifier to bootstrap a larger (n=10,000) dataset adapted from the Quora Insincere Questions dataset. With this machine-labeled data, we train a prompt classifier to predict whether ChatGPT will refuse a given question, without seeing ChatGPT's response. This prompt classifier achieves 76% accuracy on a test set of manually labeled questions (n=1,009). We examine our classifiers and the prompt n-grams that are most predictive of either compliance or refusal. Datasets and code are available at https://github.com/maxwellreuter/chatgpt-refusals.

Abstract: One problem to solve in the context of information fusion, decision-making, and other artificial intelligence challenges is to compute justified beliefs based on evidence. In real-life examples, this evidence may be inconsistent, incomplete, or uncertain, making the problem of evidence fusion highly non-trivial. In this paper, we propose a new model for measuring degrees of beliefs based on possibly inconsistent, incomplete, and uncertain evidence, by combining tools from Dempster-Shafer Theory and Topological Models of Evidence. Our belief model is more general than the aforementioned approaches in two important ways: (1) it can reproduce them when appropriate constraints are imposed, and, more notably, (2) it is flexible enough to compute beliefs according to various standards that represent agents' evidential demands. The latter novelty allows the users of our model to employ it to compute an agent's (possibly) distinct degrees of belief, based on the same evidence, in situations when, e.g, the agent prioritizes avoiding false negatives and when it prioritizes avoiding false positives. Finally, we show that computing degrees of belief with this model is #P-complete in general.

Abstract: The industry 4.0 is leveraging digital technologies and machine learning techniques to connect and optimize manufacturing processes. Central to this idea is the ability to transform raw data into human understandable knowledge for reliable data-driven decision-making. Convolutional Neural Networks (CNNs) have been instrumental in processing image data, yet, their ``black box'' nature complicates the understanding of their prediction process. In this context, recent advances in the field of eXplainable Artificial Intelligence (XAI) have proposed the extraction and localization of concepts, or which visual cues intervene on the prediction process of CNNs. This paper tackles the application of concept extraction (CE) methods to industry 4.0 scenarios. To this end, we modify a recently developed technique, ``Extracting Concepts with Local Aggregated Descriptors'' (ECLAD), improving its scalability. Specifically, we propose a novel procedure for calculating concept importance, utilizing a wrapper function designed for CNNs. This process is aimed at decreasing the number of times each image needs to be evaluated. Subsequently, we demonstrate the potential of CE methods, by applying them in three industrial use cases. We selected three representative use cases in the context of quality control for material design (tailored textiles), manufacturing (carbon fiber reinforcement), and maintenance (photovoltaic module inspection). In these examples, CE was able to successfully extract and locate concepts directly related to each task. This is, the visual cues related to each concept, coincided with what human experts would use to perform the task themselves, even when the visual cues were entangled between multiple classes. Through empirical results, we show that CE can be applied for understanding CNNs in an industrial context, giving useful insights that can relate to domain knowledge.

Abstract: We utilise the power of Large Language Models (LLMs), in particular GPT4, to be prompt engineered into performing an arbitrary task. Here, we give the model some human priors via text, along with some typical procedures for solving the ARC tasks, and ask it to generate the i) broad description of the input-output relation, ii) detailed steps of the input-output mapping, iii) use the detailed steps to perform manipulation on the test input and derive the test output. The current GPT3.5/GPT4 prompt solves 2 out of 4 tested small ARC challenges (those with small grids of 8x8 and below). With tweaks to the prompt to make it more specific for the use case, it can solve more. We posit that when scaled to a multi-agent system with usage of past memory and equipped with an image interpretation tool via Visual Question Answering, we may actually be able to solve the majority of the ARC challenge

Abstract: In this paper, drawing inspiration from the human creativity literature, we explore the optimal balance between novelty and usefulness in generative Artificial Intelligence (AI) systems. We posit that overemphasizing either aspect can lead to limitations such as hallucinations and memorization. Hallucinations, characterized by AI responses containing random inaccuracies or falsehoods, emerge when models prioritize novelty over usefulness. Memorization, where AI models reproduce content from their training data, results from an excessive focus on usefulness, potentially limiting creativity. To address these challenges, we propose a framework that includes domain-specific analysis, data and transfer learning, user preferences and customization, custom evaluation metrics, and collaboration mechanisms. Our approach aims to generate content that is both novel and useful within specific domains, while considering the unique requirements of various contexts.

Abstract: Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. Recent studies have demonstrated that LLMs can assist an algorithm agent in solving complex sequential decision making tasks in embodied environments by providing high-level instructions. However, interacting with LLMs can be time-consuming, as in many practical scenarios, they require a significant amount of storage space that can only be deployed on remote cloud server nodes. Additionally, using commercial LLMs can be costly since they may charge based on usage frequency. In this paper, we explore how to enable efficient and cost-effective interactions between the agent and an LLM. We propose a reinforcement learning based mediator model that determines when it is necessary to consult LLMs for high-level instructions to accomplish a target task. Experiments on 4 MiniGrid environments that entail planning sub-goals demonstrate that our method can learn to solve target tasks with only a few necessary interactions with an LLM, significantly reducing interaction costs in testing environments, compared with baseline methods. Experimental results also suggest that by learning a mediator model to interact with the LLM, the agent's performance becomes more robust against both exploratory and stochastic environments.

Abstract: Knowledge graphs (KGs) are an important tool for representing complex relationships between entities in the biomedical domain. Several methods have been proposed for learning embeddings that can be used to predict new links in such graphs. Some methods ignore valuable attribute data associated with entities in biomedical KGs, such as protein sequences, or molecular graphs. Other works incorporate such data, but assume that entities can be represented with the same data modality. This is not always the case for biomedical KGs, where entities exhibit heterogeneous modalities that are central to their representation in the subject domain. We propose a modular framework for learning embeddings in KGs with entity attributes, that allows encoding attribute data of different modalities while also supporting entities with missing attributes. We additionally propose an efficient pretraining strategy for reducing the required training runtime. We train models using a biomedical KG containing approximately 2 million triples, and evaluate the performance of the resulting entity embeddings on the tasks of link prediction, and drug-protein interaction prediction, comparing against methods that do not take attribute data into account. In the standard link prediction evaluation, the proposed method results in competitive, yet lower performance than baselines that do not use attribute data. When evaluated in the task of drug-protein interaction prediction, the method compares favorably with the baselines. We find settings involving low degree entities, which make up for a substantial amount of the set of entities in the KG, where our method outperforms the baselines. Our proposed pretraining strategy yields significantly higher performance while reducing the required training runtime. Our implementation is available at https://github.com/elsevier-AI-Lab/BioBLP .

Abstract: Knowledge graph embedding models (KGEMs) have gained considerable traction in recent years. These models learn a vector representation of knowledge graph entities and relations, a.k.a. knowledge graph embeddings (KGEs). Learning versatile KGEs is desirable as it makes them useful for a broad range of tasks. However, KGEMs are usually trained for a specific task, which makes their embeddings task-dependent. In parallel, the widespread assumption that KGEMs actually create a semantic representation of the underlying entities and relations (e.g., project similar entities closer than dissimilar ones) has been challenged. In this work, we design heuristics for generating protographs -- small, modified versions of a KG that leverage schema-based information. The learnt protograph-based embeddings are meant to encapsulate the semantics of a KG, and can be leveraged in learning KGEs that, in turn, also better capture semantics. Extensive experiments on various evaluation benchmarks demonstrate the soundness of this approach, which we call Modular and Agnostic SCHema-based Integration of protograph Embeddings (MASCHInE). In particular, MASCHInE helps produce more versatile KGEs that yield substantially better performance for entity clustering and node classification tasks. For link prediction, using MASCHInE has little impact on rank-based performance but increases the number of semantically valid predictions.

Abstract: Ontologies often require knowledge representation on multiple levels of abstraction, but description logics (DLs) are not well-equipped for supporting this. We propose an extension of DLs in which abstraction levels are first-class citizens and which provides explicit operators for the abstraction and refinement of concepts and roles across multiple abstraction levels, based on conjunctive queries. We prove that reasoning in the resulting family of DLs is decidable while several seemingly harmless variations turn out to be undecidable. We also pinpoint the precise complexity of our logics and several relevant fragments.

Abstract: Art curatorial processes are characterized by the presentation of a collection of artworks in a knowledgeable way. Machine processes are characterized by their capacity to manage and analyze large amounts of data. This paper envisages machine curation and audience interaction as a means to explore the implications of contemporary AI models for the curatorial world. This project was developed for the occasion of the 2023 Helsinki Art Biennial, entitled New Directions May Emerge. We use the Helsinki Art Museum (HAM) collection to re-imagine the city of Helsinki through the lens of machine perception. We use visual-textual models to place artworks currently hosted inside the museum in outdoor public spaces of the city, assigning fictional coordinates based on similarity scores. Synthetic 360{\deg} art panoramas are generated using diffusion-based models to propose a machinic visual style guided by the artworks. The result of this project will be virtually presented as a web-based installation, where such a re-contextualization allows the navigation of an alternative version of the city while exploring its artistic heritage. Finally, we discuss our contributions to machine curation and the ethical implications that such a process entails. The web-based installation is available at this link: http://newlyformedcity.com/.

Abstract: Load safety assessment and compliance is an essential step in the corporate process of every logistics service provider. In 2020, a total of 11,371 police checks of trucks were carried out, during which 9.6% (1091) violations against the load safety regulations were detected. For a logistic service provider, every load safety violation results in height fines and damage to reputation. An assessment of load safety supported by artificial intelligence (AI) will reduce the risk of accidents by unsecured loads and fines during safety assessments. This work shows how photos of the load, taken by the truck driver or the loadmaster after the loading process, can be used to assess load safety. By a trained two-stage artificial neural network (ANN), these photos are classified into three different classes I) cargo loaded safely, II) cargo loaded unsafely, and III) unusable image. By applying several architectures of convolutional neural networks (CNN), it can be shown that it is possible to distinguish between unusable and usable images for cargo safety assessment. This distinction is quite crucial since the truck driver and the loadmaster sometimes provide photos without the essential image features like the case structure of the truck and the whole cargo. A human operator or another ANN will then assess the load safety within the second stage.

Abstract: The use of von Neumann -- Morgenstern utility is examined in the context of multiple choices between lotteries. Different conclusions are reached if the choices are simultaneous or sequential. It is demonstrated that utility cannot be additive.

Abstract: Driver support systems that include human states in the support process is an active research field. Many recent approaches allow, for example, to sense the driver's drowsiness or awareness of the driving situation. However, so far, this rich information has not been utilized much for improving the effectiveness of support systems. In this paper, we therefore propose a warning system that uses human states in the form of driver errors and can warn users in some cases of upcoming risks several seconds earlier than the state of the art systems not considering human factors. The system consists of a behavior planner Risk Maps which directly changes its prediction of the surrounding driving situation based on the sensed driver errors. By checking if this driver's behavior plan is objectively safe, a more robust and foresighted driver warning is achieved. In different simulations of a dynamic lane change and intersection scenarios, we show how the driver's behavior plan can become unsafe, given the estimate of driver errors, and experimentally validate the advantages of considering human factors.

Abstract: This paper presents a rich knowledge representation language aimed at formalizing causal knowledge. This language is used for accurately and directly formalizing common benchmark examples from the literature of actual causality. A definition of cause is presented and used to analyze the actual causes of changes with respect to sequences of actions representing those examples.

Abstract: Large language models (LLMs) with memory are computationally universal. However, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by biological brains. Due to their approximate nature and proneness to the accumulation of errors, conventional neural memory mechanisms cannot support LLMs to simulate complex reasoning. In this paper, we seek inspiration from modern computer architectures to augment LLMs with symbolic memory for complex multi-hop reasoning. Such a symbolic memory framework is instantiated as an LLM and a set of SQL databases, where the LLM generates SQL instructions to manipulate the SQL databases. We validate the effectiveness of the proposed memory framework on a synthetic dataset requiring complex reasoning. The project website is available at https://chatdatabase.github.io/ .