arXiv subjects

Kristian Kersting

Publications and source records attributed to Kristian Kersting.

At least 91 records · Page 5Linked to original sources

arXiv2025

LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies

Building safe Large Language Models (LLMs) across multiple languages is essential in ensuring both safe access and linguistic diversity. To this end, we conduct a large-scale, comprehensive safety evaluation of the current LLM landscape. For this purpose, we introduce M-ALERT, a multilingual benchmark that evaluates the safety of LLMs in five languages: English, French, German, Italian, and Spanish. M-ALERT includes 15k high-quality prompts per language, totaling 75k, with category-wise annotations. Our extensive experiments on 39 state-of-the-art LLMs highlight the importance of language-specific safety analysis, revealing that models often exhibit significant inconsistencies in safety across languages and categories. For instance, Llama3.2 shows high unsafety in category crime_tax for Italian but remains safe in other languages. Similar inconsistencies can be observed across all models. In contrast, certain categories, such as substance_cannabis and crime_propaganda, consistently trigger unsafe responses across models and languages. These findings underscore the need for robust multilingual safety practices in LLMs to ensure responsible usage across diverse communities.

cs.CL↗

arXiv2025

How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions

Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted towards synthetic training captions. While this setup is generally believed to produce more capable models, current literature does not provide any insights into its design choices. This study closes this gap by systematically investigating how different synthetic captioning strategies impact the downstream performance of text-to-image models. Our experiments demonstrate that dense, high-quality captions enhance text alignment but may introduce trade-offs in output aesthetics and diversity. Conversely, captions of randomized lengths yield balanced improvements across aesthetics and alignment without compromising sample diversity. We also demonstrate that varying caption distributions introduce significant shifts in the output bias of a trained model. Our findings underscore the importance of caption design in achieving optimal model performance and provide practical insights for more effective training data strategies in text-to-image generation.

cs.CV↗

arXiv2025

Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess

In games like chess, strategy evolves dramatically across distinct phases - the opening, middlegame, and endgame each demand different forms of reasoning and decision-making. Yet, many modern chess engines rely on a single neural network to play the entire game uniformly, often missing opportunities to specialize. In this work, we introduce M2CTS, a modular framework that combines Mixture of Experts with Monte Carlo Tree Search to adapt strategy dynamically based on game phase. We explore three different methods for training the neural networks: Separated Learning, Staged Learning, and Weighted Learning. By routing decisions through specialized neural networks trained for each phase, M2CTS improves both computational efficiency and playing strength. In experiments on chess, M2CTS achieves up to +122 Elo over standard single-model baselines and shows promising generalization to multi-agent domains such as Pommerman. These results highlight how modular, phase-aware systems can better align with the structured nature of games and move us closer to human-like behavior in dividing a problem into many smaller units.

cs.LG↗

arXiv2025

Where is the Truth? The Risk of Getting Confounded in a Continual World

A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting where confounders may vary in time across tasks, the challenge of mitigating the effect of confounders far exceeds the standard forgetting problem normally considered. In particular, we provide a formal description of such continual confounders and identify that, in general, spurious correlations are easily ignored when training for all tasks jointly, but it is harder to avoid confounding when they are considered sequentially. These descriptions serve as a basis for constructing a novel CLEVR-based continually confounded dataset, which we term the ConCon dataset. Our evaluations demonstrate that standard continual learning methods fail to ignore the dataset's confounders. Overall, our work highlights the challenges of confounding factors, particularly in continual learning settings, and demonstrates the need for developing continual learning methods to robustly tackle these.

cs.LG↗

arXiv2025

Right on Time: Revising Time Series Models by Constraining their Explanations

Deep time series models often suffer from reliability issues due to their tendency to rely on spurious correlations, leading to incorrect predictions. To mitigate such shortcuts and prevent "Clever-Hans" moments in time series models, we introduce Right on Time (RioT), a novel method that enables interacting with model explanations across both the time and frequency domains. By incorporating feedback on explanations in both domains, RioT constrains the model, steering it away from annotated spurious correlations. This dual-domain interaction strategy is crucial for effectively addressing shortcuts in time series datasets. We empirically demonstrate the effectiveness of RioT in guiding models toward more reliable decision-making across popular time series classification and forecasting datasets, as well as our newly recorded dataset with naturally occuring shortcuts, P2S, collected from a real mechanical production line.

cs.LG↗

arXiv2025

LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

This paper introduces LlavaGuard, a suite of VLM-based vision safeguards that address the critical need for reliable guardrails in the era of large-scale data and models. To this end, we establish a novel open framework, describing a customizable safety taxonomy, data preprocessing, augmentation, and training setup. For teaching a VLM safeguard on safety, we further create a multimodal safety dataset with high-quality human expert annotations, where each image is labeled with a safety rating, category, and rationale. We also employ advanced augmentations to support context-specific assessments. The resulting LlavaGuard models, ranging from 0.5B to 7B, serve as a versatile tool for evaluating the safety compliance of visual content against flexible policies. In comprehensive experiments, LlavaGuard outperforms both state-of-the-art safeguards and VLMs in accuracy and in flexibly handling different policies. Additionally, we demonstrate LlavaGuard's performance in two real-world applications: large-scale dataset annotation and moderation of text-to-image models. We make our entire framework, including the dataset, model weights, and training code.

cs.CV↗

arXiv2025

Causal Explanations Over Time: Articulated Reasoning for Interactive Environments

Structural Causal Explanations (SCEs) can be used to automatically generate explanations in natural language to questions about given data that are grounded in a (possibly learned) causal model. Unfortunately they work for small data only. In turn they are not attractive to offer reasons for events, e.g., tracking causal changes over multiple time steps, or a behavioral component that involves feedback loops through actions of an agent. To this end, we generalize SCEs to a (recursive) formulation of explanation trees to capture the temporal interactions between reasons. We show the benefits of this more general SCE algorithm on synthetic time-series data and a 2D grid game, and further compare it to the base SCE and other existing methods for causal explanations.

cs.AI↗

arXiv2025

Forecasting Company Fundamentals

Company fundamentals are key to assessing companies' financial and overall success and stability. Forecasting them is important in multiple fields, including investing and econometrics. While statistical and contemporary machine learning methods have been applied to many time series tasks, there is a lack of comparison of these approaches on this particularly challenging data regime. To this end, we try to bridge this gap and thoroughly evaluate the theoretical properties and practical performance of 24 deterministic and probabilistic company fundamentals forecasting models on real company data. We observe that deep learning models provide superior forecasting performance to classical models, in particular when considering uncertainty estimation. To validate the findings, we compare them to human analyst expectations and find that their accuracy is comparable to the automatic forecasts. We further show how these high-quality forecasts can benefit automated stock allocation. We close by presenting possible ways of integrating domain experts to further improve performance and increase reliability.

q-fin.ST↗

arXiv2025

Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You

Text-to-image generation models have recently achieved astonishing results in image quality, flexibility, and text alignment, and are consequently employed in a fast-growing number of applications. Through improvements in multilingual abilities, a larger community now has access to this technology. However, our results show that multilingual models suffer from significant gender biases just as monolingual models do. Furthermore, the natural expectation that multilingual models will provide similar results across languages does not hold up. Instead, there are important differences between languages. We propose a novel benchmark, MAGBIG, intended to foster research on gender bias in multilingual models. We use MAGBIG to investigate the effect of multilingualism on gender bias in T2I models. To this end, we construct multilingual prompts requesting portraits of people with a certain occupation or trait. Our results show that not only do models exhibit strong gender biases but they also behave differently across languages. Furthermore, we investigate prompt engineering strategies, such as indirect, neutral formulations, to mitigate these biases. Unfortunately, these approaches have limited success and result in worse text-to-image alignment. Consequently, we call for more research into diverse representations across languages in image generators, as well as into steerability to address biased model behavior.

cs.CL↗

arXiv2025

STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond

Critical text assessment is at the core of many expert activities, such as fact-checking, peer review, and essay grading. Yet, existing work treats critical text assessment as a black box problem, limiting interpretability and human-AI collaboration. To close this gap, we introduce Structured Reasoning In Critical Text Assessment (STRICTA), a novel specification framework to model text assessment as an explicit, step-wise reasoning process. STRICTA breaks down the assessment into a graph of interconnected reasoning steps drawing on causality theory (Pearl, 1995). This graph is populated based on expert interaction data and used to study the assessment process and facilitate human-AI collaboration. We formally define STRICTA and apply it in a study on biomedical paper assessment, resulting in a dataset of over 4000 reasoning steps from roughly 40 biomedical experts on more than 20 papers. We use this dataset to empirically study expert reasoning in critical text assessment, and investigate if LLMs are able to imitate and support experts within these workflows. The resulting tools and datasets pave the way for studying collaborative expert-AI reasoning in text assessment, in peer review and beyond.

cs.CL↗

arXiv2025

Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models

High-quality multilingual training data is essential for effectively pretraining large language models (LLMs). Yet, the availability of suitable open-source multilingual datasets remains limited. Existing state-of-the-art datasets mostly rely on heuristic filtering methods, restricting both their cross-lingual transferability and scalability. Here, we introduce JQL, a systematic approach that efficiently curates diverse and high-quality multilingual data at scale while significantly reducing computational demands. JQL distills LLMs' annotation capabilities into lightweight annotators based on pretrained multilingual embeddings. These models exhibit robust multilingual and cross-lingual performance, even for languages and scripts unseen during training. Evaluated empirically across 35 languages, the resulting annotation pipeline substantially outperforms current heuristic filtering methods like Fineweb2. JQL notably enhances downstream model training quality and increases data retention rates. Our research provides practical insights and valuable resources for multilingual data curation, raising the standards of multilingual dataset development.

cs.CL↗

arXiv2025

EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition

Effective human-AI interaction relies on AI's ability to accurately perceive and interpret human emotions. Current benchmarks for vision and vision-language models are severely limited, offering a narrow emotional spectrum that overlooks nuanced states (e.g., bitterness, intoxication) and fails to distinguish subtle differences between related feelings (e.g., shame vs. embarrassment). Existing datasets also often use uncontrolled imagery with occluded faces and lack demographic diversity, risking significant bias. To address these critical gaps, we introduce EmoNet Face, a comprehensive benchmark suite. EmoNet Face features: (1) A novel 40-category emotion taxonomy, meticulously derived from foundational research to capture finer details of human emotional experiences. (2) Three large-scale, AI-generated datasets (EmoNet HQ, Binary, and Big) with explicit, full-face expressions and controlled demographic balance across ethnicity, age, and gender. (3) Rigorous, multi-expert annotations for training and high-fidelity evaluation. (4) We built EmpathicInsight-Face, a model achieving human-expert-level performance on our benchmark. The publicly released EmoNet Face suite - taxonomy, datasets, and model - provides a robust foundation for developing and evaluating AI systems with a deeper understanding of human emotions.

cs.CV↗

arXiv2025

Deep Reinforcement Learning Agents are not even close to Human Intelligence

Deep reinforcement learning (RL) agents achieve impressive results in a wide variety of tasks, but they lack zero-shot adaptation capabilities. While most robustness evaluations focus on tasks complexifications, for which human also struggle to maintain performances, no evaluation has been performed on tasks simplifications. To tackle this issue, we introduce HackAtari, a set of task variations of the Arcade Learning Environments. We use it to demonstrate that, contrary to humans, RL agents systematically exhibit huge performance drops on simpler versions of their training tasks, uncovering agents' consistent reliance on shortcuts. Our analysis across multiple algorithms and architectures highlights the persistent gap between RL agents and human behavioral intelligence, underscoring the need for new benchmarks and methodologies that enforce systematic generalization testing beyond static evaluation protocols. Training and testing in the same environment is not enough to obtain agents equipped with human-like intelligence.

cs.LG↗

arXiv2025

Hyperparameter Optimization via Interacting with Probabilistic Circuits

Despite the growing interest in designing truly interactive hyperparameter optimization (HPO) methods, to date, only a few allow to include human feedback. Existing interactive Bayesian optimization (BO) methods incorporate human beliefs by weighting the acquisition function with a user-defined prior distribution. However, in light of the non-trivial inner optimization of the acquisition function prevalent in BO, such weighting schemes do not always accurately reflect given user beliefs. We introduce a novel BO approach leveraging tractable probabilistic models named probabilistic circuits (PCs) as a surrogate model. PCs encode a tractable joint distribution over the hybrid hyperparameter space and evaluation scores. They enable exact conditional inference and sampling. Based on conditional sampling, we construct a novel selection policy that enables an acquisition function-free generation of candidate points (thereby eliminating the need for an additional inner-loop optimization) and ensures that user beliefs are reflected accurately in the selection policy. We provide a theoretical analysis and an extensive empirical evaluation, demonstrating that our method achieves state-of-the-art performance in standard HPO and outperforms interactive BO baselines in interactive HPO.

cs.LG↗

arXiv2025

Guidelines for the Quality Assessment of Energy-Aware NAS Benchmarks

Neural Architecture Search (NAS) accelerates progress in deep learning through systematic refinement of model architectures. The downside is increasingly large energy consumption during the search process. Surrogate-based benchmarking mitigates the cost of full training by querying a pre-trained surrogate to obtain an estimate for the quality of the model. Specifically, energy-aware benchmarking aims to make it possible for NAS to favourably trade off model energy consumption against accuracy. Towards this end, we propose three design principles for such energy-aware benchmarks: (i) reliable power measurements, (ii) a wide range of GPU usage, and (iii) holistic cost reporting. We analyse EA-HAS-Bench based on these principles and find that the choice of GPU measurement API has a large impact on the quality of results. Using the Nvidia System Management Interface (SMI) on top of its underlying library influences the sampling rate during the initial data collection, returning faulty low-power estimations. This results in poor correlation with accurate measurements obtained from an external power meter. With this study, we bring to attention several key considerations when performing energy-aware surrogate-based benchmarking and derive first guidelines that can help design novel benchmarks. We show a narrow usage range of the four GPUs attached to our device, ranging from 146 W to 305 W in a single-GPU setting, and narrowing down even further when using all four GPUs. To improve holistic energy reporting, we propose calibration experiments over assumptions made in popular tools, such as Code Carbon, thus achieving reductions in the maximum inaccuracy from 10.3 % to 8.9 % without and to 6.6 % with prior estimation of the expected load on the device.

cs.LG↗

arXiv2025

Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning

When tackling complex problems, humans naturally break them down into smaller, manageable subtasks and adjust their initial plans based on observations. For instance, if you want to make coffee at a friend's place, you might initially plan to grab coffee beans, go to the coffee machine, and pour them into the machine. Upon noticing that the machine is full, you would skip the initial steps and proceed directly to brewing. In stark contrast, state of the art reinforcement learners, such as Proximal Policy Optimization (PPO), lack such prior knowledge and therefore require significantly more training steps to exhibit comparable adaptive behavior. Thus, a central research question arises: \textit{How can we enable reinforcement learning (RL) agents to have similar ``human priors'', allowing the agent to learn with fewer training interactions?} To address this challenge, we propose differentiable symbolic planner (Dylan), a novel framework that integrates symbolic planning into Reinforcement Learning. Dylan serves as a reward model that dynamically shapes rewards by leveraging human priors, guiding agents through intermediate subtasks, thus enabling more efficient exploration. Beyond reward shaping, Dylan can work as a high level planner that composes primitive policies to generate new behaviors while avoiding common symbolic planner pitfalls such as infinite execution loops. Our experimental evaluations demonstrate that Dylan significantly improves RL agents' performance and facilitates generalization to unseen tasks.

cs.AI↗

arXiv2025

BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and rules. This disjointed approach severely limits the agents' capabilities, as they often lack either the flexible low-level reaction characteristic of neural agents or the interpretable reasoning of symbolic agents. To overcome this challenge, we introduce BlendRL, a neuro-symbolic RL framework that harmoniously integrates both paradigms within RL agents that use mixtures of both logic and neural policies. We empirically demonstrate that BlendRL agents outperform both neural and symbolic baselines in standard Atari environments, and showcase their robustness to environmental changes. Additionally, we analyze the interaction between neural and symbolic policies, illustrating how their hybrid use helps agents overcome each other's limitations.

cs.LG↗

arXiv2025

Systems with Switching Causal Relations: A Meta-Causal Perspective

Most work on causality in machine learning assumes that causal relationships are driven by a constant underlying process. However, the flexibility of agents' actions or tipping points in the environmental process can change the qualitative dynamics of the system. As a result, new causal relationships may emerge, while existing ones change or disappear, resulting in an altered causal graph. To analyze these qualitative changes on the causal graph, we propose the concept of meta-causal states, which groups classical causal models into clusters based on equivalent qualitative behavior and consolidates specific mechanism parameterizations. We demonstrate how meta-causal states can be inferred from observed agent behavior, and discuss potential methods for disentangling these states from unlabeled data. Finally, we direct our analysis towards the application of a dynamical system, showing that meta-causal states can also emerge from inherent system dynamics, and thus constitute more than a context-dependent framework in which mechanisms emerge only as a result of external factors.

cs.LG↗