Conversational agents (CA s) based on generative artificial intelligence frequently face challenges ensuring ethical interactions that align with human values. Current value alignment efforts largely rely on top - down approaches, such as technical guidelines or legal value principles. However, these methods tend to be disconnec ted from the specific contexts in which CAs operate, potentially leading to misalignment with users' interests. To address this challenge, we propose a novel, bottom - up approach to value alignment, utilizing the value ontology of the ISO Value - Based Engine ering standard for ethical IT design. We analyse 593 ethically sensitive system outputs identified from 16,908 conversational logs of a major European employment service CA to identify core values and instances of value misalignment within real - world inter actions. The results revealed nine core values and 32 different value misalignments that negatively impacted users. Our findings provide actionable insights for CA providers seeking to address ethical challenges and achieve more context - sensitive value ali gnment.

To overcome these significant challenges, we propose two novel architectures designed to integrate domain knowledge about drug side effects into a Llama 3 - 8B Language Model: Retrieval Augmented Generation (RAG) and GraphRAG. Our first architecture employs RAG, which enhances LLMs by retrieving relevant information from an external Pinecone vector database where drug side effect information is stored as feature vectors. The second architecture utilizes GraphRAG, which leverages a Neo4j graph database to stor e and efficiently handle more complex relationships of drug side effect associations. Both frameworks incorporate custom split functions and filtering modules to optimize user prompts for accurate retrieval. Through extensive evaluations on 19,520 associat ions between 976 marketed drugs and 3,851 unique side effect terms, we demonstrate that GraphRAG achieves near - perfect accuracy in drug side effect retrieval, significantly outperforming standalone LLMs and standard RAG approaches.

Motivation: Unanticipated drug-drug interactions (DDIs) pose significant risks in polypharmacy, emphasizing the need for predictive methods. Recent advancements in computational techniques aim to address this challenge. Methods: We introduce ADEP, a novel approach integrating a discriminator and an encoder-decoder model to address data sparsity and enhance feature extraction. ADEP employs a three-part model, including multiple classification methods, to predict adverse effects in polypharmacy. Results: Evaluation on benchmark datasets shows ADEP outperforms well-known methods such as GGI-DDI, SSF-DDI, LSFC, DPSP, GNN-DDI, MSTE, MDF-SA-DDI, NNPS, DDIMDL, Random Forest, K-Nearest-Neighbor, Logistic Regression, and Decision Tree. Key metrics include Accuracy, AUROC, AUPRC, F-score, Recall, Precision, False Negatives, and False Positives. ADEP achieves more accurate predictions of adverse effects in polypharmacy. A case study with real-world data illustrates ADEP's practical application in identifying potential DDIs and preventing adverse effects. Conclusions: ADEP significantly advances the prediction of polypharmacy adverse effects, offering improved accuracy and reliability. Its innovative architecture enhances feature extraction from sparse medical data, improving medication safety and patient outcomes. Availability: Source code and datasets are available at https://github.com/m0hssn/ADEP.

Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables data holders to adhere strictly to data protection regulations. However, existing unlearning techniques face practical constraints, often causing performance degradation, demanding brief fine-tuning post unlearning, and requiring significant storage. In response, this paper introduces a novel class of machine unlearning algorithms. First method is partial amnesiac unlearning, integration of layer-wise pruning with amnesiac unlearning. In this method, updates made to the model during training are pruned and stored, subsequently used to forget specific data from trained model. The second method assimilates layer-wise partial-updates into label-flipping and optimization-based unlearning to mitigate the adverse effects of data deletion on model efficacy. Through a detailed experimental evaluation, we showcase the effectiveness of proposed unlearning methods. Experimental results highlight that the partial amnesiac unlearning not only preserves model efficacy but also eliminates the necessity for brief post fine-tuning, unlike conventional amnesiac unlearning. Moreover, employing layer-wise partial updates in label-flipping and optimization-based unlearning techniques demonstrates superiority in preserving model efficacy compared to their naive counterparts.

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the internet. We study what model developers can do if they detect that some data was manipulated or incorrect. Such manipulated data can cause adverse effects like vulnerability to backdoored samples, systematic biases, and in general, reduced accuracy on certain input domains. Often, all manipulated training samples are not known, and only a small, representative subset of the affected data is flagged. We formalize "Corrective Machine Unlearning" as the problem of mitigating the impact of data affected by unknown manipulations on a trained model, possibly knowing only a subset of impacted samples. We demonstrate that the problem of corrective unlearning has significantly different requirements from traditional privacy-oriented unlearning. We find most existing unlearning methods, including the gold-standard retraining-from-scratch, require most of the manipulated data to be identified for effective corrective unlearning. However, one approach, SSD, achieves limited success in unlearning adverse effects with just a small portion of the manipulated samples, showing the tractability of this setting. We hope our work spurs research towards developing better methods for corrective unlearning and offers practitioners a new strategy to handle data integrity challenges arising from web-scale training.

Background: Polypharmacy, i.e. taking five drugs or more, is both a public health and an economic issue. Medication reviews are structured interviews of the patient by the community pharmacist, aiming at optimizing the drug treatment and deprescribing useless, redundant or dangerous drugs. However, they remain difficult to perform and time-consuming. Several clinical decision support systems were developed for helping clinicians to manage polypharmacy. However, most were limited to the implementation of clinical practice guidelines. In this work, our objective is to design an innovative clinical decision support system for medication reviews and polypharmacy management, named ABiMed. Methods: ABiMed associates several approaches: guidelines implementation, but the automatic extraction of patient data from the GP's electronic health record and its transfer to the pharmacist, and the visual presentation of contextualized drug knowledge using visual analytics. We performed an ergonomic assessment and qualitative evaluations involving pharmacists and GPs during focus groups and workshops. Results: We describe the proposed architecture, which allows a collaborative multi-user usage. We present the various screens of ABiMed for entering or verifying patient data, for accessing drug knowledge (posology, adverse effects, interactions), for viewing STOPP/START rules and for suggesting modification to the treatment. Qualitative evaluations showed that health professionals were highly interested by our approach, associating the automatic guidelines execution with the visual presentation of drug knowledge. Conclusions: The association of guidelines implementation with visual presentation of knowledge is a promising approach for managing polypharmacy. Future works will focus on the improvement and the evaluation of ABiMed.

Ensuring fairness in decision-making systems within Human-Cyber-Physical-Systems (HCPS) is a pressing concern, particularly when diverse individuals, each with varying behaviors and expectations, coexist within the same application space, influenced by a shared set of control actions in the system. The long-term adverse effects of these actions further pose the challenge, as historical experiences and interactions shape individual perceptions of fairness. This paper addresses the challenge of fairness from an equity perspective of adverse effects, taking into account the dynamic nature of human behavior and evolving preferences while recognizing the lasting impact of adverse effects. We formally introduce the concept of Fairness-in-Adverse-Effects (FinA) within the HCPS context. We put forth a comprehensive set of five formulations for FinA, encompassing both the instantaneous and long-term aspects of adverse effects. To empirically validate the effectiveness of our FinA approach, we conducted an evaluation within the domain of smart homes, a pertinent HCPS application. The outcomes of our evaluation demonstrate that the adoption of FinA significantly enhances the overall perception of fairness among individuals, yielding an average improvement of 66.7% when compared to the state-of-the-art method.

Tabular data prediction has been employed in medical applications such as patient health risk prediction. However, existing methods usually revolve around the algorithm design while overlooking the significance of data engineering. As such, previous predictors are often trained on manually curated small datasets that struggle to generalize across different tabular datasets during inference. This paper proposes to scale medical tabular data predictors (MediTab) to various tabular inputs with varying features. The method uses a data engine that leverages large language models (LLMs) to consolidate tabular samples to overcome the barrier across tables with distinct schema. It also aligns out-domain data with the target task using a "learn, annotate, and refinement" pipeline. The expanded training data then enables the pre-trained MediTab to infer for arbitrary tabular input in the domain without fine-tuning, resulting in significant improvements over supervised baselines: it reaches an average ranking of 1.57 and 1.00 on 7 patient outcome prediction datasets and 3 trial outcome prediction datasets, respectively. In addition, MediTab exhibits impressive zero-shot performances: it outperforms supervised XGBoost models by 8.9% and 17.2% on average in two prediction tasks, respectively. Tabular data are structured as tables or spreadsheets in a relational database. Each row in the table represents a data sample, while columns represent various feature variables of different types, including categorical, numerical, binary, and textual features. Most previous papers focused on the model design of tabular predictors, mainly by (1) augmenting feature interactions via neural networks (Arik & Pfister, 2021), (2) improving tabular data representation learning by self-supervised pre-training (Yin et al., 2020; Yoon et al., 2020; Bahri et al., 2022), and (3) performing cross-tabular pre-training for transfer learning (Wang & Sun, 2022b; Zhu et al., 2023). Tabular data predictor was also employed in medicine, such as patient health risk prediction (Wang & Sun, 2022b) and clinical trial outcome prediction (Fu et al., 2022). Additionally, LLMs have been shown to be able to sample synthetic and yet highly realistic tabular data as well Borisov et al. (2022); Theodorou et al. (2023).

Opioid related aberrant behaviors (ORAB) present novel risk factors for opioid overdose. Previously, ORAB have been mainly assessed by survey results and by monitoring drug administrations. Such methods however, cannot scale up and do not cover the entire spectrum of aberrant behaviors. On the other hand, ORAB are widely documented in electronic health record notes. This paper introduces a novel biomedical natural language processing benchmark dataset named ODD, for ORAB Detection Dataset. ODD is an expert-annotated dataset comprising of more than 750 publicly available EHR notes. ODD has been designed to identify ORAB from patients' EHR notes and classify them into nine categories; 1) Confirmed Aberrant Behavior, 2) Suggested Aberrant Behavior, 3) Opioids, 4) Indication, 5) Diagnosed opioid dependency, 6) Benzodiapines, 7) Medication Changes, 8) Central Nervous System-related, and 9) Social Determinants of Health. We explored two state-of-the-art natural language processing (NLP) models (finetuning pretrained language models and prompt-tuning approaches) to identify ORAB. Experimental results show that the prompt-tuning models outperformed the finetuning models in most cateogories and the gains were especially higher among uncommon categories (Suggested aberrant behavior, Diagnosed opioid dependency and Medication change). Although the best model achieved the highest 83.92% on area under precision recall curve, uncommon classes (Suggested Aberrant Behavior, Diagnosed Opioid Dependence, and Medication Change) still have a large room for performance improvement.

Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series. However, the adversarial robustness of incremental learners has not been widely verified, leaving potential security risks. Specifically, for poisoning-based backdoor attacks, we argue that the nature of streaming data in IL provides great convenience to the adversary by creating the possibility of distributed and cross-task attacks -- an adversary can affect \textbf{any unknown} previous or subsequent task by data poisoning \textbf{at any time or time series} with extremely small amount of backdoor samples injected (e.g., $0.1\%$ based on our observations). To attract the attention of the research community, in this paper, we empirically reveal the high vulnerability of 11 typical incremental learners against poisoning-based backdoor attack on 3 learning scenarios, especially the cross-task generalization effect of backdoor knowledge, while the poison ratios range from $5\%$ to as low as $0.1\%$. Finally, the defense mechanism based on activation clustering is found to be effective in detecting our trigger pattern to mitigate potential security risks.