The auditing of financial documents, traditionally a labor-intensive task, is a promising field of application for Artificial Intelligence. Recommendation systems are capable of suggesting the most relevant passages from financial reports that meet accounting standards’ legal requirements. However, testing if the compliance requirements are satisfied is a non-trivial task. In this work, we tackle this problem from two directions. Our first approach leverages Large Language Models which we fine-tune specifically f or compliance checks. Our results show an improvement in performance over the generic baseline LLMs. A disadvantage of LLMs is that they result in high inference costs. For this reason, we explore a second approach in which we use smaller models that come with reduced running costs. Despite their smaller size, these models also show promising predictive performance.

This study explores efficient algorithms to enhance user matching in Unrare.me, a novel social networking platform designed to connect individuals affected by rare diseases. Our primary objective is to develop a recommender system that identifies and suggests users with similar medical conditions, facilitating meaningful connections within these unique communities. Utilizing textual user profile data, we train sentence embedder models to generate similar embeddings for users that have rated each other high. We investigate various fine-tuning strategies, as well as a hybrid approach between a dense embedder and sparse SPLADE embeddings. Furthermore, we investigate the efficacy of various clustering algorithms, such as TopicBERT for thematic analysis, K-Means for centroid-based grouping, and Latent Dirichlet Allocation (LDA) for probabilistic topic modeling, to reduce the matching complexity and enable better scalability of the platform.

We present RepLLaMA, a neural ranking model for optimizing patient matching in rare disease communities. Using data from Unrare.me consisting of over two thousand profiles and over ten thousand ratings, our bi-encoder architecture maps profiles to 4096-dimensional vectors, enabling efficient similarity computations. The system processes unstructured symptom descriptions and structured responses, incorporating expert-guided LLM enhancements. Results show Top-10 Recall of 49.36%$(\pm 2.03)$, surpassing baselines while maintaining generalization. The implementation provides a scalable solution for rare disease patient matching, addressing computational complexity challenges.

With over 7,000 known rare diseases and a prevalence of less than one in a thousand, rare diseases pose substantial challenges to advanced medical support networks. This study investigates the efficacy of Unrare.me, a novel social networking platform designed for individuals affected by rare diseases, including patients, their family members, and medical professionals, addressing data sparsity and combinatorial complexities in user matching. We demonstrate that simple matching heuristics already serve as a decent basis for collecting user feedback on match quality. Leveraging over 10,000 user matching feedback scores from more than 2,000 active users, we evaluate algorithms including collaborative filtering and user embedding similarity with state-of-the-art Large Language Models (LLMs). With a top-10 and top-5 hit-rate of 55% and 37%, respectively, we show that a combination of medical data augmentation and embeddings significantly enhances performance beyond the initial heuristic baseline.

We present the Automated List Inspection (ALI) tool that utilizes methods from machine learning, natural language processing, combined with domain expert knowledge to automate financial statement auditing. ALI is a content based context-aware recommender system, that matches relevant text passages from the notes to the financial statement to specific law regulations. In this paper, we present the architecture of the recommender tool which includes text mining, language modeling, unsupervised and supervised methods that range from binary classification models to deep recurrent neural networks. Next to our main findings, we present quantitative and qualitative comparisons of the algorithms as well as concepts for how to further extend the functionality of the tool.