arXiv subjects

David Berghaus

Publications and source records attributed to David Berghaus.

26 records · Page 2Linked to original sources

arXiv2025

Reasoning LLMs in the Medical Domain: A Literature Survey

The emergence of advanced reasoning capabilities in Large Language Models (LLMs) marks a transformative development in healthcare applications. Beyond merely expanding functional capabilities, these reasoning mechanisms enhance decision transparency and explainability-critical requirements in medical contexts. This survey examines the transformation of medical LLMs from basic information retrieval tools to sophisticated clinical reasoning systems capable of supporting complex healthcare decisions. We provide a thorough analysis of the enabling technological foundations, with a particular focus on specialized prompting techniques like Chain-of-Thought and recent breakthroughs in Reinforcement Learning exemplified by DeepSeek-R1. Our investigation evaluates purpose-built medical frameworks while also examining emerging paradigms such as multi-agent collaborative systems and innovative prompting architectures. The survey critically assesses current evaluation methodologies for medical validation and addresses persistent challenges in field interpretation limitations, bias mitigation strategies, patient safety frameworks, and integration of multimodal clinical data. Through this survey, we seek to establish a roadmap for developing reliable LLMs that can serve as effective partners in clinical practice and medical research.

cs.AI↗

arXiv2025

Towards Unified Multimodal Financial Forecasting: Integrating Sentiment Embeddings and Market Indicators via Cross-Modal Attention

We propose STONK (Stock Optimization using News Knowledge), a multimodal framework integrating numerical market indicators with sentiment-enriched news embeddings to improve daily stock-movement prediction. By combining numerical & textual embeddings via feature concatenation and cross-modal attention, our unified pipeline addresses limitations of isolated analyses. Backtesting shows STONK outperforms numeric-only baselines. A comprehensive evaluation of fusion strategies and model configurations offers evidence-based guidance for scalable multimodal financial forecasting. Source code is available on GitHub

cs.AI↗

arXiv2025

Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory Compliance

Risk and Quality (R&Q) assurance in highly regulated industries requires constant navigation of complex regulatory frameworks, with employees handling numerous daily queries demanding accurate policy interpretation. Traditional methods relying on specialized experts create operational bottlenecks and limit scalability. We present a novel Retrieval Augmented Generation (RAG) system leveraging Large Language Models (LLMs), hybrid search and relevance boosting to enhance R&Q query processing. Evaluated on 124 expert-annotated real-world queries, our actively deployed system demonstrates substantial improvements over traditional RAG approaches. Additionally, we perform an extensive hyperparameter analysis to compare and evaluate multiple configuration setups, delivering valuable insights to practitioners.

cs.CL↗

arXiv2025

Foundation Inference Models for Markov Jump Processes

Markov jump processes are continuous-time stochastic processes which describe dynamical systems evolving in discrete state spaces. These processes find wide application in the natural sciences and machine learning, but their inference is known to be far from trivial. In this work we introduce a methodology for zero-shot inference of Markov jump processes (MJPs), on bounded state spaces, from noisy and sparse observations, which consists of two components. First, a broad probability distribution over families of MJPs, as well as over possible observation times and noise mechanisms, with which we simulate a synthetic dataset of hidden MJPs and their noisy observation process. Second, a neural network model that processes subsets of the simulated observations, and that is trained to output the initial condition and rate matrix of the target MJP in a supervised way. We empirically demonstrate that one and the same (pretrained) model can infer, in a zero-shot fashion, hidden MJPs evolving in state spaces of different dimensionalities. Specifically, we infer MJPs which describe (i) discrete flashing ratchet systems, which are a type of Brownian motors, and the conformational dynamics in (ii) molecular simulations, (iii) experimental ion channel data and (iv) simple protein folding models. What is more, we show that our model performs on par with state-of-the-art models which are finetuned to the target datasets.

cs.LG↗

arXiv2023

A Database of Modular Forms on Noncongruence Subgroups

We present a database of several hundred modular forms up to and including weight six on noncongruence subgroups of index $\leq 17$. In addition, our database contains expressions for the Belyi map for genus zero subgroups and equations of the corresponding elliptic curves for genus one subgroups and numerical approximations of noncongruence Eisenstein series to 1500 digits precision.

math.NT↗

arXiv2022

Computation of Laplacian eigenvalues of two-dimensional shapes with dihedral symmetry

We numerically compute the lowest Laplacian eigenvalues of several two-dimensional shapes with dihedral symmetry at arbitrary precision arithmetic. Our approach is based on the method of particular solutions with domain decomposition. We are particularly interested in asymptotic expansions of the eigenvalues $λ(n)$ of shapes with $n$ edges that are of the form $λ(n) \sim x\sum_{k=0}^{\infty} \frac{C_k(x)}{n^k}$ where $x$ is the limiting eigenvalue for $n\rightarrow \infty$. Expansions of this form have previously only been known for regular polygons with Dirichlet boundary condition and (quite surprisingly) involve Riemann zeta values and single-valued multiple zeta values, which makes them interesting to study. We provide numerical evidence for closed-form expressions of higher order $C_k(x)$ and give more examples of shapes for which such expansions are possible (including regular polygons with Neumann boundary condition, regular star polygons and star shapes with sinusoidal boundary).

math.NA↗

arXiv2022

On the computation of modular forms on noncongruence subgroups

We present two approaches that can be used to compute modular forms on noncongruence subgroups. The first approach uses Hejhal's method for which we improve the arbitrary precision solving techniques so that the algorithm becomes about up to two orders of magnitude faster in practical computations. This allows us to obtain high precision numerical estimates of the Fourier coefficients from which the algebraic expressions can be identified using the LLL algorithm. The second approach is restricted to genus zero subgroups and uses efficient methods to compute the Belyi map from which the modular forms can be constructed.

math.NT↗

arXiv2021

On Dirichlet eigenvalues of regular polygons

We prove that the first Dirichlet eigenvalue of a regular $N$-gon of area $π$ has an asymptotic expansion of the form $λ_1(1+\sum_{n\ge3}C_n(λ_1)N^{-n})$ as $N\to\infty$, where $λ_1$ is the first Dirichlet eigenvalue of the unit disk and $C_n$ are polynomials whose coefficients belong to the space of multiple zeta values of weight $n$. We also explicitly compute these polynomials for all $n\le14$.

math.NT↗