arXiv subjects

Matthias Busch

Publications and source records attributed to Matthias Busch.

7 recordsLinked to original sources

arXiv2026

Molecular D\'ej\`a Vu: Digit-Level Retrieval of Published Values in Frontier Language Models

Large language models (LLMs) are increasingly evaluated on molecular property benchmarks, but accuracy cannot distinguish a model that predicts a property from one that retrieves a published number. We audit 22 frontier models on 12 regression benchmarks for verbatim retrieval and find that it is widespread but relatively benchmark-specific: on five datasets more than $50\%$ of the LLMs show verbatim retrieval, while on the remaining datasets it appears only in isolated cells. We run our experiments at two reasoning levels and find that reasoning changes retrieval. The same experiments, on the same molecules and with the same prompt, are flagged $89\%$ more often at the higher reasoning level than at the lowest one. Finally, we test a way to interrupt retrieval in our most contaminated cases, and find that the strongest models in some cases still recognise a combination of transformed SMILES strings and original labels. Furthermore, suppressing retrieval moves the prediction errors of the different models closer together in relative terms, while their differing use of verbatim retrieval spreads them apart. This indicates that the general predictive capability of an LLM is not determined solely by the amount of memorised values. This work provides an overview of the amount and depth of verbatim retrieval in molecular regression benchmarks using LLMs.

cs.AI↗

arXiv2026

LLM-driven design of physics-constrained constitutive models: two agents are better than one

Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scientific programming. Large language models (LLMs) have recently been shown to lower this barrier by generating constitutive models on demand, but existing single-agent pipelines lack systematic checks that the resulting models respect fundamental physical laws. To close this gap, we introduce the first multi-agent LLM-driven approach for constitutive model generation: a Creator agent proposes a model tailored to the data, while an Inspector agent critically audits each proposal against nine physical constraints and returns it for refinement whenever a violation is detected. We demonstrate this concept with constitutive artificial neural networks (CANNs) and benchmark it on brain tissue and rubber as isotropic materials, and on porcine skin tissue as a transversely isotropic material with a preferred fiber direction, using two different LLM backbones (Claude Opus 4.7 and Kimi K2.5). Whether a generated model satisfies the physical constraints is assessed numerically, by probing each constraint across a broad sample of deformation states, rotations, and perturbation directions. Adding the Inspector raises the share of exported models that pass all these checks from 90\% to 95\% for Opus and from 47\% to 60\% for Kimi. In addition, the generated models are on par with or even surpass expert-designed models in accuracy, extrapolate reliably beyond the training data, and generalize remarkably well to unseen loading paths. Separating generation from inspection thus turns LLM-driven constitutive modeling into a substantially more trustworthy process. The paradigm is deliberately technique-agnostic...

cs.LG↗

arXiv2026

In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts

The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains ambiguous, particularly given the potential for training data contamination in widely used benchmarks. This paper investigates whether LLMs perform genuine in-context regression on molecular properties or instead rely on verbatim retrieval of memorized target values. Furthermore, we analyze the interplay between pre-trained knowledge and in-context information through a series of progressively blinded experiments. We evaluate nine LLM variants across three families (GPT-4.1, GPT-5, Gemini 2.5) on three MoleculeNet datasets (Delaney solubility, Lipophilicity, QM7 atomization energy) using a systematic blinding approach that iteratively reduces available information, complemented by 0-, 60-, and 1000-shot in-context sample sizes as an additional control for information access. To validate the memorization analysis and the blinding experiments, we add a positive and a negative control for the memorization experiments and structural reference baselines for the multi-shot experiments as well as bootstrap confidence intervals for all results. We find no evidence of verbatim retrieval on the legacy benchmarks and show that blinding exposes conflicts between pre-trained knowledge and in-context information. This work provides a principled framework for evaluating molecular property prediction under controlled information access.

cs.LG↗

arXiv2025

Automating modeling in mechanics: LLMs as designers of physics-constrained neural networks for constitutive modeling of materials

Large language model (LLM)-based agentic frameworks increasingly adopt the paradigm of dynamically generating task-specific agents. We suggest that not only agents but also specialized software modules for scientific and engineering tasks can be generated on demand. We demonstrate this concept in the field of solid mechanics. There, so-called constitutive models are required to describe the relationship between mechanical stress and body deformation. Constitutive models are essential for both the scientific understanding and industrial application of materials. However, even recent data-driven methods of constitutive modeling, such as constitutive artificial neural networks (CANNs), still require substantial expert knowledge and human labor. We present a framework in which an LLM generates a CANN on demand, tailored to a given material class and dataset provided by the user. The framework covers LLM-based architecture selection, integration of physical constraints, and complete code generation. Evaluation on three benchmark problems demonstrates that LLM-generated CANNs achieve accuracy comparable to or greater than manually engineered counterparts, while also exhibiting reliable generalization to unseen loading scenarios and extrapolation to large deformations. These findings indicate that LLM-based generation of physics-constrained neural networks can substantially reduce the expertise required for constitutive modeling and represent a step toward practical end-to-end automation.

cs.LG↗

arXiv2025

Chatbots to strengthen democracy: An interdisciplinary seminar to train identifying argumentation techniques of science denial

In recent times, discussions on social media platforms have increasingly come under scrutiny due to the proliferation of science denial and fake news. Traditional solutions, such as regulatory actions, have been implemented to mitigate the spread of misinformation; however, these measures alone are not sufficient. To complement these efforts, educational approaches are becoming essential in empowering users to critically engage with misinformation. Conversation training, through serious games or personalized methods, has emerged as a promising strategy to help users handle science denial and toxic conversation tactics. This paper suggests an interdisciplinary seminar to explore the suitability of Large Language Models (LLMs) acting as a persona of a science denier to support people in identifying misinformation and improving resilience against toxic interactions. In the seminar, groups of four to five students will develop an AI-based chatbot that enables realistic interactions with science-denial argumentation structures. The task involves planning the setting, integrating a Large Language Model to facilitate natural dialogues, implementing the chatbot using the RASA framework, and evaluating the outcomes in a user study. It is crucial that users understand what they need to do during the interaction, how to conclude it, and how the relevant information is conveyed. The seminar does not aim to develop chatbots for practicing debunking but serves to teach AI technologies and test the feasibility of this idea for future applications. The chatbot seminar is conducted as a hybrid, parallel master's module at the participating educational institutions.

cs.CY↗

arXiv2025

Machine-learned domain partitioning for computationally efficient coupling of continuum and particle simulations of membrane fabrication

All simulation approaches eventually face limits in computational scalability when applied to large spatiotemporal domains. This challenge becomes especially apparent in molecular-level particle simulations, where high spatial and temporal resolution leads to rapidly increasing computational demands. To overcome these limitations, hybrid methods that combine simulations with different levels of resolution offer a promising solution. In this context, we present a machine learning-based decision model that dynamically selects between simulation methods at runtime. The model is built around a Multilayer perceptron (MLP) that predicts the expected discrepancy between particle and continuum simulation results, enabling the localized use of high-fidelity particle simulations only where they are expected to add value. This concurrent approach is applied to the simulation of membrane fabrication processes, where a particle simulation is coupled with a continuum model. This article describes the architecture of the decision model and its integration into the simulation workflow, enabling efficient, scalable, and adaptive multiscale simulations.

physics.comp-ph↗

arXiv2024

Active partitioning: inverting the paradigm of active learning

Datasets often incorporate various functional patterns related to different aspects or regimes, which are typically not equally present throughout the dataset. We propose a novel, general-purpose partitioning algorithm that utilizes competition between models to detect and separate these functional patterns. This competition is induced by multiple models iteratively submitting their predictions for the dataset, with the best prediction for each data point being rewarded with training on that data point. This reward mechanism amplifies each model's strengths and encourages specialization in different patterns. The specializations can then be translated into a partitioning scheme. The amplification of each model's strengths inverts the active learning paradigm: while active learning typically focuses the training of models on their weaknesses to minimize the number of required training data points, our concept reinforces the strengths of each model, thus specializing them. We validate our concept -- called active partitioning -- with various datasets with clearly distinct functional patterns, such as mechanical stress and strain data in a porous structure. The active partitioning algorithm produces valuable insights into the datasets' structure, which can serve various further applications. As a demonstration of one exemplary usage, we set up modular models consisting of multiple expert models, each learning a single partition, and compare their performance on more than twenty popular regression problems with single models learning all partitions simultaneously. Our results show significant improvements, with up to 54% loss reduction, confirming our partitioning algorithm's utility.

cs.LG↗