Research Papers

The rapid adoption of generative artificial intelligence (AI) in scientific research, particularly large language models (LLMs), has outpaced the development of ethical guidelines, leading to a "Triple-Too" problem: too many high-level ethical initiatives, too abstract principles lacking contextual and practical relevance, and too much focus on restrictions and risks over benefits and utilities. Existing approaches--principlism (reliance on abstract ethical principles), formalism (rigid application of rules), and technological solutionism (overemphasis on technological fixes)--offer little practical guidance for addressing ethical challenges of AI in scientific research practices. To bridge the gap between abstract principles and day-to-day research practices, a user-centered, realism-inspired approach is proposed here. It outlines five specific goals for ethical AI use: 1) understanding model training and output, including bias mitigation strategies; 2) respecting privacy, confidentiality, and copyright; 3) avoiding plagiarism and policy violations; 4) applying AI beneficially compared to alternatives; and 5) using AI transparently and reproducibly. Each goal is accompanied by actionable strategies and realistic cases of misuse and corrective measures. I argue that ethical AI application requires evaluating its utility against existing alternatives rather than isolated performance metrics. Additionally, I propose documentation guidelines to enhance transparency and reproducibility in AI-assisted research. Moving forward, we need targeted professional development, training programs, and balanced enforcement mechanisms to promote responsible AI use while fostering innovation. By refining these ethical guidelines and adapting them to emerging AI capabilities, we can accelerate scientific progress without compromising research integrity.

The organizational use of artificial intelligence (AI) has rapidly spread across various sectors. Alongside the awareness of the benefits brought by AI, there is a growing consensus on the necessity of tackling the risks and potential harms, such as bias and discrimination, brought about by advanced AI technologies. A multitude of AI ethics principles have been proposed to tackle these risks, but the outlines of organizational processes and practices for ensuring socially responsible AI development are in a nascent state. To address the paucity of comprehensive governance models, we present an AI governance framework, the hourglass model of organizational AI governance, which targets organizations that develop and use AI systems. The framework is designed to help organizations deploying AI systems translate ethical AI principles into practice and align their AI systems and processes with the forthcoming European AI Act. The hourglass framework includes governance requirements at the environmental, organizational, and AI system levels. At the AI system level, we connect governance requirements to AI system life cycles to ensure governance throughout the system's life span. The governance model highlights the systemic nature of AI governance and opens new research avenues into its practical implementation, the mechanisms that connect different AI governance layers, and the dynamics between the AI governance actors. The model also offers a starting point for organizational decision-makers to consider the governance components needed to ensure social acceptability, mitigate risks, and realize the potential of AI.

With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI) design, recent efforts have produced user interfaces (UIs) for AI experts to investigate the fairness of AI models. In this work, we provide a design space exploration that supports not only data scientists but also domain experts to investigate AI fairness. Using loan applications as an example, we held a series of workshops with loan officers and data scientists to elicit their requirements. We instantiated these requirements into FairHIL, a UI to support human-in-the-loop fairness investigations, and describe how this UI could be generalized to other use cases. We evaluated FairHIL through a think-aloud user study. Our work contributes better designs to investigate an AI model's fairness-and move closer towards responsible AI.

We propose a new model for regulation to achieve AI safety: global regulatory markets. We first sketch the model in general terms and provide an overview of the costs and benefits of this approach. We then demonstrate how the model might work in practice: responding to the risk of adversarial attacks on AI models employed in commercial drones.

A Guide to Feature Importance Methods for Scientific Inference

Fiona Katharina Ewald, Ludwig Bothmann, Marvin N. Wright +3

While machine learning (ML) models are increasingly used due to their high predictive power, their use in understanding the data-generating process (DGP) is limited. Understanding the DGP requires insights into feature-target associations, which many ML models cannot directly provide due to their opaque internal mechanisms. Feature importance (FI) methods provide useful insights into the DGP under certain conditions. Since the results of different FI methods have different interpretations, selecting the correct FI method for a concrete use case is crucial and still requires expert knowledge. This paper serves as a comprehensive guide to help understand the different interpretations of global FI methods. Through an extensive review of FI methods and providing new proofs regarding their interpretation, we facilitate a thorough understanding of these methods and formulate concrete recommendations for scientific inference. We conclude by discussing options for FI uncertainty estimation and point to directions for future research aiming at full statistical inference from black-box ML models.

Foundation Model Transparency Reports

Rishi Bommasani, Kevin Klyman, Shayne Longpre +5

Foundation models are critical digital technologies with sweeping societal impact that necessitates transparency. To codify how foundation model developers should provide transparency about the development and deployment of their models, we propose Foundation Model Transparency Reports, drawing upon the transparency reporting practices in social media. While external documentation of societal harms prompted social media transparency reports, our objective is to institutionalize transparency reporting for foundation models while the industry is still nascent. To design our reports, we identify 6 design principles given the successes and shortcomings of social media transparency reporting. To further schematize our reports, we draw upon the 100 transparency indicators from the Foundation Model Transparency Index. Given these indicators, we measure the extent to which they overlap with the transparency requirements included in six prominent government policies (e.g., the EU AI Act, the US Executive Order on Safe, Secure, and Trustworthy AI). Well-designed transparency reports could reduce compliance costs, in part due to overlapping regulatory requirements across different jurisdictions. We encourage foundation model developers to regularly publish transparency reports, building upon recommendations from the G7 and the White House.

Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks

Stefan Blücher, Johanna Vielhaben, Nils Strodthoff

Feature removal is a central building block for eXplainable AI (XAI), both for occlusion-based explanations (Shapley values) as well as their evaluation (pixel flipping, PF). However, occlusion strategies can vary significantly from simple mean replacement up to inpainting with state-of-the-art diffusion models. This ambiguity limits the usefulness of occlusion-based approaches. For example, PF benchmarks lead to contradicting rankings. This is amplified by competing PF measures: Features are either removed starting with most influential first (MIF) or least influential first (LIF). This study proposes two complementary perspectives to resolve this disagreement problem. Firstly, we address the common criticism of occlusion-based XAI, that artificial samples lead to unreliable model evaluations. We propose to measure the reliability by the R(eference)-Out-of-Model-Scope (OMS) score. The R-OMS score enables a systematic comparison of occlusion strategies and resolves the disagreement problem by grouping consistent PF rankings. Secondly, we show that the insightfulness of MIF and LIF is conversely dependent on the R-OMS score. To leverage this, we combine the MIF and LIF measures into the symmetric relevance gain (SRG) measure. This breaks the inherent connection to the underlying occlusion strategy and leads to consistent rankings. This resolves the disagreement problem, which we verify for a set of 40 different occlusion strategies.

The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus

Anna Hedström, Philine Bommer, Kristoffer K. Wickstrøm +3

One of the unsolved challenges in the field of Explainable AI (XAI) is determining how to most reliably estimate the quality of an explanation method in the absence of ground truth explanation labels. Resolving this issue is of utmost importance as the evaluation outcomes generated by competing evaluation methods (or ''quality estimators''), which aim at measuring the same property of an explanation method, frequently present conflicting rankings. Such disagreements can be challenging for practitioners to interpret, thereby complicating their ability to select the best-performing explanation method. We address this problem through a meta-evaluation of different quality estimators in XAI, which we define as ''the process of evaluating the evaluation method''. Our novel framework, MetaQuantus, analyses two complementary performance characteristics of a quality estimator: its resilience to noise and reactivity to randomness, thus circumventing the need for ground truth labels. We demonstrate the effectiveness of our framework through a series of experiments, targeting various open questions in XAI such as the selection and hyperparameter optimisation of quality estimators. Our work is released under an open-source license (https://github.com/annahedstroem/MetaQuantus) to serve as a development tool for XAI- and Machine Learning (ML) practitioners to verify and benchmark newly constructed quality estimators in a given explainability context. With this work, we provide the community with clear and theoretically-grounded guidance for identifying reliable evaluation methods, thus facilitating reproducibility in the field.

We investigated the data-driven relationship between features in the tumor microenvironment (TME) and the overall and 5-year survival in triple-negative breast cancer (TNBC) and non-TNBC (NTNBC) patients by using Explainable Artificial Intelligence (XAI) models. We used clinical information from patients with invasive breast carcinoma from The Cancer Genome Atlas and from two studies from the cbioPortal, the PanCanAtlas project and the GDAC Firehose study. In this study, we used a normalized RNA sequencing data-driven cohort from 1,015 breast cancer patients, alive or deceased, from the UCSC Xena data set and performed integrated deconvolution with the EPIC method to estimate the percentage of seven different immune and stromal cells from RNA sequencing data. Novel insights derived from our XAI model showed that CD4+ T cells and B cells are more critical than other TME features for enhanced prognosis for both TNBC and NTNBC patients. Our XAI model revealed the critical inflection points (i.e., threshold fractions) of CD4+ T cells and B cells above or below which 5-year survival rates improve. Subsequently, we ascertained the conditional probabilities of $\geq$ 5-year survival in both TNBC and NTNBC patients under specific conditions inferred from the inflection points. In particular, the XAI models revealed that a B-cell fraction exceeding 0.018 in the TME could ensure 100% 5-year survival for NTNBC patients. The findings from this research could lead to more accurate clinical predictions and enhanced immunotherapies and to the design of innovative strategies to reprogram the TME of breast cancer patients.

Artificial Intelligence (AI) holds great promise for transforming healthcare, particularly in disease diagnosis, prognosis, and patient care. The increasing availability of digital medical data, such as images, omics, biosignals, and electronic health records, combined with advances in computing, has enabled AI models to approach expert-level performance. However, widespread clinical adoption remains limited, primarily due to challenges beyond technical performance, including ethical concerns, regulatory barriers, and lack of trust. To address these issues, AI systems must align with the principles of Trustworthy AI (TAI), which emphasize human agency and oversight, algorithmic robustness, privacy and data governance, transparency, bias and discrimination avoidance, and accountability. Yet, the complexity of healthcare processes (e.g., screening, diagnosis, prognosis, and treatment) and the diversity of stakeholders (clinicians, patients, providers, regulators) complicate the integration of TAI principles. To bridge the gap between TAI theory and practical implementation, this paper proposes a design framework to support developers in embedding TAI principles into medical AI systems. Thus, for each stakeholder identified across various healthcare processes, we propose a disease-agnostic collection of requirements that medical AI systems should incorporate to adhere to the principles of TAI. Additionally, we examine the challenges and tradeoffs that may arise when applying these principles in practice. To ground the discussion, we focus on cardiovascular diseases, a field marked by both high prevalence and active AI innovation, and demonstrate how TAI principles have been applied and where key obstacles persist.

This study critically examines the commonly held assumption that explicability in artificial intelligence (AI) systems inherently boosts user trust. Utilizing a meta-analytical approach, we conducted a comprehensive examination of the existing literature to explore the relationship between AI explainability and trust. Our analysis, incorporating data from 90 studies, reveals a statistically significant but moderate positive correlation between the explainability of AI systems and the trust they engender among users. This indicates that while explainability contributes to building trust, it is not the sole or predominant factor in this equation. In addition to academic contributions to the field of Explainable AI (XAI), this research highlights its broader socio-technical implications, particularly in promoting accountability and fostering user trust in critical domains such as healthcare and justice. By addressing challenges like algorithmic bias and ethical transparency, the study underscores the need for equitable and sustainable AI adoption. Rather than focusing solely on immediate trust, we emphasize the normative importance of fostering authentic and enduring trustworthiness in AI systems.

Today, crop diversification in agriculture is a critical issue to meet the increasing demand for food and improve food safety and quality. This issue is considered to be the most important challenge for the next generation of agriculture due to the diminishing natural resources, the limited arable land, and unpredictable climatic conditions caused by climate change. In this paper, we employ emerging technologies such as the Internet of Things (IoT), machine learning (ML), and explainable artificial intelligence (XAI) to improve operational efficiency and productivity in the agricultural sector. Specifically, we propose an edge computing-based explainable crop recommendation system, AgroXAI, which suggests suitable crops for a region based on weather and soil conditions. In this system, we provide local and global explanations of ML model decisions with methods such as ELI5, LIME, SHAP, which we integrate into ML models. More importantly, we provide regional alternative crop recommendations with the counterfactual explainability method. In this way, we envision that our proposed AgroXAI system will be a platform that provides regional crop diversity in the next generation agriculture.