Research Papers

The rapid advancement of Large Language Models (LLMs) has created a critical gap in consumer protection due to the lack of standardized certification processes for LLM-powered Artificial Intelligence (AI) systems. This paper argues that current regulatory approaches, which focus on compute-level thresholds and generalized model evaluations, are insufficient to ensure the safety and effectiveness of specific LLM-based user experiences. We propose a shift towards a certification process centered on actual user-facing experiences and the curation of high-quality datasets for evaluation. This approach offers several benefits: it drives consumer confidence in AI system performance, enables businesses to demonstrate the credibility of their products, and allows regulators to focus on direct consumer protection. The paper outlines a potential certification workflow, emphasizing the importance of domain-specific datasets and expert evaluation. By repositioning data as the strategic center of regulatory efforts, this framework aims to address the challenges posed by the probabilistic nature of AI systems and the rapid pace of technological advancement. This shift in regulatory focus has the potential to foster innovation while ensuring responsible AI development, ultimately benefiting consumers, businesses, and government entities alike.

Deep learning models (DLMs) achieve increasingly high performance both on structured and unstructured data. They significantly extended applicability of machine learning to various domains. Their success in making predictions, detecting patterns and generating new data made significant impact on science and industry. Despite these accomplishments, DLMs are difficult to explain because of their enormous size. In this work, we propose a novel framework for post-hoc explaining and relating DLMs using redescriptions. The framework allows cohort analysis of arbitrary DLMs by identifying statistically significant redescriptions of neuron activations. It allows coupling neurons to a set of target labels or sets of descriptive attributes, relating layers within a single DLM or associating different DLMs. The proposed framework is independent of the artificial neural network architecture and can work with more complex target labels (e.g. multi-label or multi-target scenario). Additionally, it can emulate both pedagogical and decompositional approach to rule extraction. The aforementioned properties of the proposed framework can increase explainability and interpretability of arbitrary DLMs by providing different information compared to existing explainable-AI approaches.

The profound impact of online reviews on consumer decision-making has made it crucial for businesses to manage negative reviews. Recent advancements in artificial intelligence (AI) technology have offered businesses novel and effective ways to manage and analyze substantial consumer feedback. In response to the growing demand for explainablility and transparency in AI applications, this study proposes a novel explainable AI (XAI) algorithm aimed at identifying influential negative reviews. The experiments conducted on 101,338 restaurant reviews validate the algorithm's effectiveness and provides understandable explanations from both the feature-level and word-level perspectives. By leveraging this algorithm, businesses can gain actionable insights for predicting, perceiving, and strategically responding to online negative feedback, fostering improved customer service and mitigating the potential damage caused by negative reviews.

Majority voting (MV) is the prototypical ``wisdom of the crowd'' algorithm. Theorems considering when MV is optimal for group decisions date back to Condorcet's 1785 jury \emph{decision} theorem. The same error independence assumption underlying the theorem can be used to prove a jury \emph{evaluation} theorem that does purely algebraic evaluation (AE) of juror performance based on a batch of their decisions. Three or more binary jurors are enough to obtain the only two possible statistics of their correctness on a test they took. AE is superior to MV in three ways. First, its empirical assumptions are looser and can handle jurors less than 50\% accurate in making decisions. Second, it has point-like precision in evaluating them given its assumption of error independence. This precision enables a multi-accuracy approach that has higher labeling accuracy than MV and comes with empirical uncertainty bounds. And, third, it is self-alarming about the failure of its error independence assumption. Experiments using demographic data from the American Community Survey confirm the practical utility of AE over MV. Two implications of the theorem for AI safety are discussed - a principled way to terminate infinite monitoring chains (who grades the graders?) and the super-alignment problem (how do we evaluate agents doing tasks we do not understand?).

Data and metadata documentation requirements for explainable-AI-ready (XAIR) models and data in physics-based simulation technology are discussed by analysing different perspectives from the literature on two core aspects: First, the scope of the simulation; this category is taken to include subject matter, the objective with which the simulation is conducted, and the object of reference, i.e., the simulated physical system or process. Second, the artefacts that need to be documented in order to make data and models XAIR, and modelling and simulation workflows explainable; two CEN workshop agreements, MODA and ModGra, are compared for this purpose. As a result, minimum requirements for an ontologization of the scope of simulation artefacts are formulated, and the object-objective abstractness diagram is proposed as a tool for visualizing the landscape of use cases for physics-based simulation.

Ensuring Artificial General Intelligence (AGI) reliably avoids harmful behaviors is a critical challenge, especially for systems with high autonomy or in safety-critical domains. Despite various safety assurance proposals and extreme risk warnings, comprehensive guidelines balancing AI safety and capability remain lacking. In this position paper, we propose the \textit{AI-\textbf{$45^{\circ}$} Law} as a guiding principle for a balanced roadmap toward trustworthy AGI, and introduce the \textit{Causal Ladder of Trustworthy AGI} as a practical framework. This framework provides a systematic taxonomy and hierarchical structure for current AI capability and safety research, inspired by Judea Pearl's ``Ladder of Causation''. The Causal Ladder comprises three core layers: the Approximate Alignment Layer, the Intervenable Layer, and the Reflectable Layer. These layers address the key challenges of safety and trustworthiness in AGI and contemporary AI systems. Building upon this framework, we define five levels of trustworthy AGI: perception, reasoning, decision-making, autonomy, and collaboration trustworthiness. These levels represent distinct yet progressive aspects of trustworthy AGI. Finally, we present a series of potential governance measures to support the development of trustworthy AGI.

The rapid integration of Artificial Intelligence (AI)-based systems offers benefits for various domains of the economy and society but simultaneously raises concerns due to emerging scandals. These scandals have led to the increasing importance of AI accountability to ensure that actors provide justification and victims receive compensation. However, AI accountability has a negative connotation due to its emphasis on penalizing sanctions, resulting in reactive approaches to emerging concerns. To counteract the prevalent negative view and offer a proactive approach to facilitate the AI accountability behavior of developers, we explore rewards as an alternative mechanism to sanctions. We develop a theoretical model grounded in Self-Determination Theory to uncover the potential impact of rewards and sanctions on AI developers. We further identify typical sanctions and bug bounties as potential reward mechanisms by surveying related research from various domains, including cybersecurity.

Synthetic datasets are important for evaluating and testing machine learning models. When evaluating real-life recommender systems, high-dimensional categorical (and sparse) datasets are often considered. Unfortunately, there are not many solutions that would allow generation of artificial datasets with such characteristics. For that purpose, we developed a novel framework for generating synthetic datasets that are diverse and statistically coherent. Our framework allows for creation of datasets with controlled attributes, enabling iterative modifications to fit specific experimental needs, such as introducing complex feature interactions, feature cardinality, or specific distributions. We demonstrate the framework's utility through use cases such as benchmarking probabilistic counting algorithms, detecting algorithmic bias, and simulating AutoML searches. Unlike existing methods that either focus narrowly on specific dataset structures, or prioritize (private) data synthesis through real data, our approach provides a modular means to quickly generating completely synthetic datasets we can tailor to diverse experimental requirements. Our results show that the framework effectively isolates model behavior in unique situations and highlights its potential for significant advancements in the evaluation and development of recommender systems. The readily-available framework is available as a free open Python package to facilitate research with minimal friction.

GPT versus Humans: Uncovering Ethical Concerns in Conversational Generative AI-empowered Multi-Robot Systems

Rebekah Rousi, Niko Makitalo, Hooman Samani +5

The emergence of generative artificial intelligence (GAI) and large language models (LLMs) such ChatGPT has enabled the realization of long-harbored desires in software and robotic development. The technology however, has brought with it novel ethical challenges. These challenges are compounded by the application of LLMs in other machine learning systems, such as multi-robot systems. The objectives of the study were to examine novel ethical issues arising from the application of LLMs in multi-robot systems. Unfolding ethical issues in GPT agent behavior (deliberation of ethical concerns) was observed, and GPT output was compared with human experts. The article also advances a model for ethical development of multi-robot systems. A qualitative workshop-based method was employed in three workshops for the collection of ethical concerns: two human expert workshops (N=16 participants) and one GPT-agent-based workshop (N=7 agents; two teams of 6 agents plus one judge). Thematic analysis was used to analyze the qualitative data. The results reveal differences between the human-produced and GPT-based ethical concerns. Human experts placed greater emphasis on new themes related to deviance, data privacy, bias and unethical corporate conduct. GPT agents emphasized concerns present in existing AI ethics guidelines. The study contributes to a growing body of knowledge in context-specific AI ethics and GPT application. It demonstrates the gap between human expert thinking and LLM output, while emphasizing new ethical concerns emerging in novel technology.

High-impact and potentially dangerous capabilities can and should be broken down into early warning shots long before reaching red lines. Each of these early warning shots should correspond to a precursory capability. Each precursory capability sits on a spectrum indicating its proximity to a final high-impact capability, corresponding to a red line. To meaningfully detect and track capability progress, we propose a taxonomy of dangerous capability zones (a zoning taxonomy) tied to a staggered information exchange framework that enables relevant bodies to take action accordingly. In the Frontier AI Safety Commitments, signatories commit to sharing more detailed information with trusted actors, including an appointed body, as appropriate (Commitment VII). Building on our zoning taxonomy, this paper makes four recommendations for specifying information sharing as detailed in Commitment VII. (1) Precursory capabilities should be shared as soon as they become known through internal evaluations before deployment. (2) AI Safety Institutes (AISIs) should be the trusted actors appointed to receive and coordinate information on precursory components. (3) AISIs should establish adequate information protection infrastructure and guarantee increased information security as precursory capabilities move through the zones and towards red lines, including, if necessary, by classifying the information on precursory capabilities or marking it as controlled. (4) High-impact capability progress in one geographical region may translate to risk in other regions and necessitates more comprehensive risk assessment internationally. As such, AISIs should exchange information on precursory capabilities with other AISIs, relying on the existing frameworks on international classified exchanges and applying lessons learned from other regulated high-risk sectors.

The downstream use cases, benefits, and risks of AI models depend significantly on what sort of access is provided to the model, and who it is provided to. Though existing safety frameworks and AI developer usage policies recognise that the risk posed by a given model depends on the level of access provided to a given audience, the procedures they use to make decisions about model access are ad hoc, opaque, and lacking in empirical substantiation. This paper consequently proposes that frontier AI companies build on existing safety frameworks by outlining transparent procedures for making decisions about model access, which we term Responsible Access Policies (RAPs). We recommend that, at a minimum, RAPs should include the following: i) processes for empirically evaluating model capabilities given different styles of access, ii) processes for assessing the risk profiles of different categories of user, and iii) clear and robust pre-commitments regarding when to grant or revoke specific types of access for particular groups under specified conditions.

This study presents DhondtXAI as a SHAP-independent, D'Hondt-based attribution framework for tabular XAI. Instead of model-native feature importance or SHAP values, DhondtXAI computes background-interventional removal effects, separates positive and negative evidence, forms optional feature alliances, applies optional thresholds, allocates seats via the D'Hondt rule, and projects onto the local model-output difference. Completeness is preserved by construction, with the projection residual ratio reported as a diagnostic. The method is evaluated on synthetic additive and interaction tests, correlated-feature perturbations, operator and apportionment ablations, projection-mode comparisons, logit-scale checks, repeated split validation, paired deletion tests, and two healthcare datasets: Wisconsin Diagnostic Breast Cancer (CatBoost) and early-stage diabetes risk prediction (XGBoost). SHAP serves only as an external comparator with aligned settings. In additive synthetics, DhondtXAI exactly recovers ground-truth rankings; in multiplicative interactions, alliances reduce the mean projection residual from 0.2527 to 0.0001. On WDBC and diabetes data, it shows high agreement with SHAP (Spearman rho = 0.9273 and 0.9353), supported by further signed, top-k, magnitude, deletion, and sensitivity analyses. Results position DhondtXAI as a complementary proportional, alliance-aware, and threshold-aware tabular XAI method, not a replacement for SHAP or LIME.