Artificial Intelligence (cs.AI)

Abstract: Clinical notes are assigned ICD codes - sets of codes for diagnoses and procedures. In the recent years, predictive machine learning models have been built for automatic ICD coding. However, there is a lack of widely accepted benchmarks for automated ICD coding models based on large-scale public EHR data. This paper proposes a public benchmark suite for ICD-10 coding using a large EHR dataset derived from MIMIC-IV, the most recent public EHR dataset. We implement and compare several popular methods for ICD coding prediction tasks to standardize data preprocessing and establish a comprehensive ICD coding benchmark dataset. This approach fosters reproducibility and model comparison, accelerating progress toward employing automated ICD coding in future studies. Furthermore, we create a new ICD-9 benchmark using MIMIC-IV data, providing more data points and a higher number of ICD codes than MIMIC-III. Our open-source code offers easy access to data processing steps, benchmark creation, and experiment replication for those with MIMIC-IV access, providing insights, guidance, and protocols to efficiently develop ICD coding models.

Abstract: Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts. However, state-of-the-art concept-based models rely on high-dimensional concept embedding representations which lack a clear semantic meaning, thus questioning the interpretability of their decision process. To overcome this limitation, we propose the Deep Concept Reasoner (DCR), the first interpretable concept-based model that builds upon concept embeddings. In DCR, neural networks do not make task predictions directly, but they build syntactic rule structures using concept embeddings. DCR then executes these rules on meaningful concept truth degrees to provide a final interpretable and semantically-consistent prediction in a differentiable manner. Our experiments show that DCR: (i) improves up to +25% w.r.t. state-of-the-art interpretable concept-based models on challenging benchmarks (ii) discovers meaningful logic rules matching known ground truths even in the absence of concept supervision during training, and (iii), facilitates the generation of counterfactual examples providing the learnt rules as guidance.

Abstract: Explainable AI (XAI) aims to answer ethical and legal questions associated with the deployment of AI models. However, a considerable number of domain-specific reviews highlight the need of a mathematical foundation for the key notions in the field, considering that even the term "explanation" still lacks a precise definition. These reviews also advocate for a sound and unifying formalism for explainable AI, to avoid the emergence of ill-posed questions, and to help researchers navigate a rapidly growing body of knowledge. To the authors knowledge, this paper is the first attempt to fill this gap by formalizing a unifying theory of XAI. Employing the framework of category theory, and feedback monoidal categories in particular, we first provide formal definitions for all essential terms in explainable AI. Then we propose a taxonomy of the field following the proposed structure, showing how the introduced theory can be used to categorize all the main classes of XAI systems currently studied in literature. In summary, the foundation of XAI proposed in this paper represents a significant tool to properly frame future research lines, and a precious guidance for new researchers approaching the field.

Abstract: Many decision-making problems feature multiple objectives. In such problems, it is not always possible to know the preferences of a decision-maker for different objectives. However, it is often possible to observe the behavior of decision-makers. In multi-objective decision-making, preference inference is the process of inferring the preferences of a decision-maker for different objectives. This research proposes a Dynamic Weight-based Preference Inference (DWPI) algorithm that can infer the preferences of agents acting in multi-objective decision-making problems, based on observed behavior trajectories in the environment. The proposed method is evaluated on three multi-objective Markov decision processes: Deep Sea Treasure, Traffic, and Item Gathering. The performance of the proposed DWPI approach is compared to two existing preference inference methods from the literature, and empirical results demonstrate significant improvements compared to the baseline algorithms, in terms of both time requirements and accuracy of the inferred preferences. The Dynamic Weight-based Preference Inference algorithm also maintains its performance when inferring preferences for sub-optimal behavior demonstrations. In addition to its impressive performance, the Dynamic Weight-based Preference Inference algorithm does not require any interactions during training with the agent whose preferences are inferred, all that is required is a trajectory of observed behavior.

Abstract: It is challenging to quantify numerical preferences for different objectives in a multi-objective decision-making problem. However, the demonstrations of a user are often accessible. We propose an algorithm to infer linear preference weights from either optimal or near-optimal demonstrations. The algorithm is evaluated in three environments with two baseline methods. Empirical results demonstrate significant improvements compared to the baseline algorithms, in terms of both time requirements and accuracy of the inferred preferences. In future work, we plan to evaluate the algorithm's effectiveness in a multi-agent system, where one of the agents is enabled to infer the preferences of an opponent using our preference inference algorithm.

Abstract: AI and ML models have already found many applications in critical domains, such as healthcare and criminal justice. However, fully automating such high-stakes applications can raise ethical or fairness concerns. Instead, in such cases, humans should be assisted by automated systems so that the two parties reach a joint decision, stemming out of their interaction. In this work we conduct an empirical study to identify how uncertainty estimates and model explanations affect users' reliance, understanding, and trust towards a model, looking for potential benefits of bringing the two together. Moreover, we seek to assess how users' behaviour is affected by their own self-confidence in their abilities to perform a certain task, while we also discuss how the latter may distort the outcome of an analysis based on agreement and switching percentages.

Abstract: Many complex scenarios require the coordination of agents possessing unique points of view and distinct semantic commitments. In response, standpoint logic (SL) was introduced in the context of knowledge integration, allowing one to reason with diverse and potentially conflicting viewpoints by means of indexed modalities. Another multi-modal logic of import is linear temporal logic (LTL) - a formalism used to express temporal properties of systems and processes, having prominence in formal methods and fields related to artificial intelligence. In this paper, we present standpoint linear temporal logic (SLTL), a new logic that combines the temporal features of LTL with the multi-perspective modelling capacity of SL. We define the logic SLTL, its syntax, and its semantics, establish its decidability and complexity, and provide a terminating tableau calculus to automate SLTL reasoning. Conveniently, this offers a clear path to extend existing LTL reasoners with practical reasoning support for temporal reasoning in multi-perspective settings.

Abstract: Recent advancements in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. Although these models have shown promising results in tasks such as machine translation and summarization, their applicability in code generation tasks remains limited without human involvement. The complexity of programming concepts required for such tasks makes it difficult to develop evaluation metrics that align with human judgment. Token-matching-based metrics, such as BLEU, have demonstrated weak correlations with human practitioners in code generation tasks. Moreover, the utilization of human-written test suites to evaluate functional correctness can be challenging in domains with low resources. To overcome these obstacles, we propose a new evaluation framework based on the GPT-3.5 (\texttt{GPT-3.5-turbo}), for code generation assessments. Our framework addresses the limitations of existing approaches by achieving superior correlations with functional correctness and human preferences, without the need for test oracles or references. We evaluate the efficacy of our framework on two different tasks and four programming languages, comparing its performance with the state-of-the-art CodeBERTScore metric, which relies on a pre-trained model. Our results demonstrate that our framework surpasses CodeBERTScore, delivering high levels of accuracy and consistency across various programming languages and tasks. We also make our evaluation framework and datasets available to the public at \url{https://github.com/terryyz/llm-code-eval}, encouraging further research in the evaluation of code generation.

Abstract: Standpoint EL is a multi-modal extension of the popular description logic EL that allows for the integrated representation of domain knowledge relative to diverse standpoints or perspectives. Advantageously, its satisfiability problem has recently been shown to be in PTime, making it a promising framework for large-scale knowledge integration. In this paper, we show that we can further push the expressivity of this formalism, arriving at an extended logic, called Standpoint EL+, which allows for axiom negation, role chain axioms, self-loops, and other features, while maintaining tractability. This is achieved by designing a satisfiability-checking deduction calculus, which at the same time addresses the need for practical algorithms. We demonstrate the feasibility of our calculus by presenting a prototypical Datalog implementation of its deduction rules.

Abstract: In this paper, we investigate the use of data obtained from prompting a large generative language model, ChatGPT, to generate synthetic training data with the aim of augmenting data in low resource scenarios. We show that with appropriate task-specific ChatGPT prompts, we outperform the most popular existing approaches for such data augmentation. Furthermore, we investigate methodologies for evaluating the similarity of the augmented data generated from ChatGPT with the aim of validating and assessing the quality of the data generated.