Establishing and Evaluating Trustworthy AI: Overview and Research Challenges

Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a result, there has been a surge in public and academic discussions about aspects that AI systems must fulfill to be considered trustworthy. In this paper, we synthesize existing conceptualizations of trustworthy AI along six requirements: 1) human agency and oversight, 2) fairness and non-discrimination, 3) transparency and explainability, 4) robustness and accuracy, 5) privacy and security, and 6) accountability. For each one, we provide a definition, describe how it can be established and evaluated, and discuss requirement-specific research challenges. Finally, we conclude this analysis by identifying overarching research challenges across the requirements with respect to 1) interdisciplinary research, 2) conceptual clarity, 3) context-dependency, 4) dynamics in evolving systems, and 5) investigations in real-world contexts. Thus, this paper synthesizes and consolidates a wide-ranging and active discussion currently taking place in various academic sub-communities and public forums. It aims to serve as a reference for a broad audience and as a basis for future research directions.

Challenges in Implementing a Recommender System for Historical Research in the Humanities

This extended abstract describes the challenges in implementing recommender systems for digital archives in the humanities, focusing on Monasterium.net, a platform for historical legal documents. We discuss three key aspects: (i) the unique characteristics of so-called charters as items for recommendation, (ii) the complex multi-stakeholder environment, and (iii) the distinct information-seeking behavior of scholars in the humanities. By examining these factors, we aim to contribute to the development of more effective and tailored recommender systems for (digital) humanities research.

Value Identification in Multistakeholder Recommender Systems for Humanities and Historical Research: The Case of the Digital Archive Monasterium.net

Recommender systems remain underutilized in humanities and historical research, despite their potential to enhance the discovery of cultural records. This paper offers an initial value identification of the multiple stakeholders that might be impacted by recommendations in Monasterium.net, a digital archive for historical legal documents. Specifically, we discuss the diverse values and objectives of its stakeholders, such as editors, aggregators, platform owners, researchers, publishers, and funding agencies. These in-depth insights into the potentially conflicting values of stakeholder groups allow designing and adapting recommender systems to enhance their usefulness for humanities and historical research. Additionally, our findings will support deeper engagement with additional stakeholders to refine value models and evaluation metrics for recommender systems in the given domains. Our conclusions are embedded in and applicable to other digital archives and a broader cultural heritage context.

Oh, Behave! Country Representation Dynamics Created by Feedback Loops in Music Recommender Systems

Recent work suggests that music recommender systems are prone to disproportionally frequent recommendations of music from countries more prominently represented in the training data, notably the US. However, it remains unclear to what extent feedback loops in music recommendation influence the dynamics of such imbalance. In this work, we investigate the dynamics of representation of local (i.e., country-specific) and US-produced music in user profiles and recommendations. To this end, we conduct a feedback loop simulation study using the standardized LFM-2b dataset. The results suggest that most of the investigated recommendation models decrease the proportion of music from local artists in their recommendations. Furthermore, we find that models preserving average proportions of US and local music do not necessarily provide country-calibrated recommendations. We also look into popularity calibration and, surprisingly, find that the most popularity-calibrated model in our study (ItemKNN) provides the least country-calibrated recommendations. In addition, users from less represented countries (e.g., Finland) are, in the long term, most affected by the under-representation of their local music in recommendations.

AI-Powered Immersive Assistance for Interactive Task Execution in Industrial Environments

Many industrial sectors rely on well-trained employees that are able to operate complex machinery. In this work, we demonstrate an AI-powered immersive assistance system that supports users in performing complex tasks in industrial environments. Specifically, our system leverages a VR environment that resembles a juice mixer setup. This digital twin of a physical setup simulates complex industrial machinery used to mix preparations or liquids (e.g., similar to the pharmaceutical industry) and includes various containers, sensors, pumps, and flow controllers. This setup demonstrates our system's capabilities in a controlled environment while acting as a proof-of-concept for broader industrial applications. The core components of our multimodal AI assistant are a large language model and a speech-to-text model that process a video and audio recording of an expert performing the task in a VR environment. The video and speech input extracted from the expert's video enables it to provide step-by-step guidance to support users in executing complex tasks. This demonstration showcases the potential of our AI-powered assistant to reduce cognitive load, increase productivity, and enhance safety in industrial environments.

Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers

Research in various fields is currently experiencing challenges regarding the reproducibility of results. This problem is also prevalent in machine learning (ML) research. The issue arises primarily due to unpublished data and/or source code and the sensitivity of ML training conditions. Although different solutions have been proposed to address this issue, such as using ML platforms, the level of reproducibility in ML-driven research remains unsatisfactory. Therefore, in this article, we discuss the reproducibility of ML-driven research with three main aims: (i) identify the barriers to reproducibility when applying ML in research as well as categorize the barriers to different types of reproducibility (description, code, data, and experiment reproducibility), (ii) identify potential drivers such as tools, practices, and interventions that support ML reproducibility as well as distinguish between technology-driven drivers, procedural drivers, and drivers related to awareness and education, and (iii) map the drivers to the barriers. With this work, we hope to provide insights and contribute to the decision-making process regarding the adoption of different solutions to support ML reproducibility.

Transparency, Privacy, and Fairness in Recommender Systems

Recommender systems have become a pervasive part of our daily online experience, and are one of the most widely used applications of artificial intelligence and machine learning. Therefore, regulations and requirements for trustworthy artificial intelligence, for example, the European AI Act, which includes notions such as transparency, privacy, and fairness are also highly relevant for the design of recommender systems in practice. This habilitation elaborates on aspects related to these three notions in the light of recommender systems, namely: (i) transparency and cognitive models, (ii) privacy and limited preference information, and (iii) fairness and popularity bias in recommender systems. Specifically, with respect to aspect (i), we highlight the usefulness of incorporating psychological theories for a transparent design process of recommender systems. We term this type of systems psychology-informed recommender systems. In aspect (ii), we study and address the trade-off between accuracy and privacy in differentially-private recommendations. We design a novel recommendation approach for collaborative filtering based on an efficient neighborhood reuse concept, which reduces the number of users that need to be protected with differential privacy. Furthermore, we address the related issue of limited availability of user preference information, e.g., click data, in the settings of session-based and cold-start recommendations. With respect to aspect (iii), we analyze popularity bias in recommender systems. We find that the recommendation frequency of an item is positively correlated with this item's popularity. This also leads to the unfair treatment of users with little interest in popular content. Finally, we study long-term fairness dynamics in algorithmic decision support in the labor market using agent-based modeling techniques.

Making Alice Appear Like Bob: A Probabilistic Preference Obfuscation Method For Implicit Feedback Recommendation Models

Users' interaction or preference data used in recommender systems carry the risk of unintentionally revealing users' private attributes (e.g., gender or race). This risk becomes particularly concerning when the training data contains user preferences that can be used to infer these attributes, especially if they align with common stereotypes. This major privacy issue allows malicious attackers or other third parties to infer users' protected attributes. Previous efforts to address this issue have added or removed parts of users' preferences prior to or during model training to improve privacy, which often leads to decreases in recommendation accuracy. In this work, we introduce SBO, a novel probabilistic obfuscation method for user preference data designed to improve the accuracy--privacy trade-off for such recommendation scenarios. We apply SBO to three state-of-the-art recommendation models (i.e., BPR, MultVAE, and LightGCN) and two popular datasets (i.e., MovieLens-1M and LFM-2B). Our experiments reveal that SBO outperforms comparable approaches with respect to the accuracy--privacy trade-off. Specifically, we can reduce the leakage of users' protected attributes while maintaining on-par recommendation accuracy.

The Impact of Differential Privacy on Recommendation Accuracy and Popularity Bias

Collaborative filtering-based recommender systems leverage vast amounts of behavioral user data, which poses severe privacy risks. Thus, often, random noise is added to the data to ensure Differential Privacy (DP). However, to date, it is not well understood, in which ways this impacts personalized recommendations. In this work, we study how DP impacts recommendation accuracy and popularity bias, when applied to the training data of state-of-the-art recommendation models. Our findings are three-fold: First, we find that nearly all users' recommendations change when DP is applied. Second, recommendation accuracy drops substantially while recommended item popularity experiences a sharp increase, suggesting that popularity bias worsens. Third, we find that DP exacerbates popularity bias more severely for users who prefer unpopular items than for users that prefer popular items.

Take the aTrain. Introducing an Interface for the Accessible Transcription of Interviews

aTrain is an open-source and offline tool for transcribing audio data in multiple languages with CPU and NVIDIA GPU support. It is specifically designed for researchers using qualitative data generated from various forms of speech interactions with research participants. aTrain requires no programming skills, runs on most computers, does not require an internet connection, and was verified not to upload data to any server. aTrain combines OpenAI's Whisper model with speaker recognition to provide output that integrates with the popular qualitative data analysis software tools MAXQDA and ATLAS.ti. It has an easy-to-use graphical interface and is provided as a Windows-App through the Microsoft Store allowing for simple installation by researchers. The source code is freely available on GitHub. Having developed aTrain with a focus on speed on local computers, we show that the transcription time on current mobile CPUs is around 2 to 3 times the duration of the audio file using the highest-accuracy transcription models. If an entry-level graphics card is available, the transcription speed increases to 20% of the audio duration.