1 citations · 2 across the 7 of their papers we have counts for
8 papers
Molecular Déjà Vu: Digit-Level Retrieval of Molecular Properties in Frontier Language Models
Matthias Busch, Marius Tacke, Sviatlana V. Lamaka +4
Large language models (LLMs) are increasingly employed to predict molecular properties. However, prediction error alone cannot distinguish prediction from retrieval of published va…
AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
Yiderigun Borjigin, Alexander Hermann, Christian Cyron +1
The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment toward itself. This effect is well established in human judgment and decision-m…
GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement
Kartik Bali, Mahish K. Guru, Christian J Cyron +1
Adaptive volumetric finite element meshing traditionally requires iterative PDE solvers or heavily supervised, data-driven surrogates trained on large-scale simulation data. This w…
LLM-driven design of physics-constrained constitutive models: two agents are better than one
Marius Tacke, Matthias Busch, Kian Abdolazizi +4
Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scie…
In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts
Matthias Busch, Marius Tacke, Sviatlana V. Lamaka +4
The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However,…
Automating modeling in mechanics: LLMs as designers of physics-constrained neural networks for constitutive modeling of materials
Marius Tacke, Matthias Busch, Kian Abdolazizi +4
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 special…
From Model Training to Model Raising
Roland Aydin, Christian Cyron, Steve Bachelor +2
Current AI training methods align models with human values only after their core capabilities have been established, resulting in models that are easily misaligned and lack deep-ro…
Active partitioning: inverting the paradigm of active learning
Marius Tacke, Matthias Busch, Kevin Linka +2
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,…