Jonathan Fürst

Gaye Colakoglu, Gürkan Solmaz, Jonathan Fürst

This paper defines and explores the design space for information extraction (IE) from layout-rich documents using large language models (LLMs). The three core challenges of layout-aware IE with LLMs are 1) data structuring, 2) model engagement, and 3) output refinement. Our study investigates the sub-problems and methods within these core challenges, such as input representation, chunking, prompting, selection of LLMs, and multimodal models. It examines the effect of different design choices through LayIE-LLM, a new, open-source, layout-aware IE test suite, benchmarking against traditional, fine-tuned IE models. The results on two IE datasets show that LLMs require adjustment of the IE pipeline to achieve competitive performance: the optimized configuration found with LayIE-LLM achieves 13.3--37.5 F1 points more than a general-practice baseline configuration using the same LLM. To find a well-working configuration, we develop a one-factor-at-a-time (OFAT) method that achieves near-optimal results. Our method is only 0.8--1.8 points lower than the best full factorial exploration with a fraction (2.8%) of the required computation. Overall, we demonstrate that, if well-configured, general-purpose LLMs match the performance of specialized models, providing a cost-effective, finetuning-free alternative. Our test-suite is available at https://github.com/gayecolakoglu/LayIE-LLM.

Linus Stuhlmann, Michael Alexander Saxer, Jonathan Fürst

Biomedical question-answering (QA) systems require effective retrieval and generation components to ensure accuracy, efficiency, and scalability. This study systematically examines a Retrieval-Augmented Generation (RAG) system for biomedical QA, evaluating retrieval strategies and response time trade-offs. We first assess state-of-the-art retrieval methods, including BM25, BioBERT, MedCPT, and a hybrid approach, alongside common data stores such as Elasticsearch, MongoDB, and FAISS, on a ~10% subset of PubMed (2.4M documents) to measure indexing efficiency, retrieval latency, and retriever performance in the end-to-end RAG system. Based on these insights, we deploy the final RAG system on the full 24M PubMed corpus, comparing different retrievers' impact on overall performance. Evaluations of the retrieval depth show that retrieving 50 documents with BM25 before reranking with MedCPT optimally balances accuracy (0.90), recall (0.90), and response time (1.91s). BM25 retrieval time remains stable (82ms), while MedCPT incurs the main computational cost. These results highlight previously not well-known trade-offs in retrieval depth, efficiency, and scalability for biomedical QA. With open-source code, the system is fully reproducible and extensible.

Gérôme Meyer, Philip Breuer, Jonathan Fürst

Open-ended questions test a more thorough understanding than closed-ended questions and are often a preferred assessment method. However, open-ended questions are tedious to grade and subject to personal bias. Therefore, there have been efforts to speed up the grading process through automation. Short Answer Grading (SAG) systems aim to automatically score students' answers. Despite growth in SAG methods and capabilities, there exists no comprehensive short-answer grading benchmark across different subjects, grading scales, and distributions. Thus, it is hard to assess the capabilities of current automated grading methods in terms of their generalizability. In this preliminary work, we introduce the combined ASAG2024 benchmark to facilitate the comparison of automated grading systems. Combining seven commonly used short-answer grading datasets in a common structure and grading scale. For our benchmark, we evaluate a set of recent SAG methods, revealing that while LLM-based approaches reach new high scores, they still are far from reaching human performance. This opens up avenues for future research on human-machine SAG systems.

Jonathan Fürst, Catherine Kosten, Farhad Nooralahzadeh et al.

Text-to-SQL systems (also known as NL-to-SQL systems) have become an increasingly popular solution for bridging the gap between user capabilities and SQL-based data access. These systems translate user requests in natural language to valid SQL statements for a specific database. Recent Text-to-SQL systems have benefited from the rapid improvement of transformer-based language models. However, while Text-to-SQL systems that incorporate such models continuously reach new high scores on -- often synthetic -- benchmark datasets, a systematic exploration of their robustness towards different data models in a real-world, realistic scenario is notably missing. This paper provides the first in-depth evaluation of the data model robustness of Text-to-SQL systems in practice based on a multi-year international project focused on Text-to-SQL interfaces. Our evaluation is based on a real-world deployment of FootballDB, a system that was deployed over a 9 month period in the context of the FIFA World Cup 2022, during which about 6K natural language questions were asked and executed. All of our data is based on real user questions that were asked live to the system. We manually labeled and translated a subset of these questions for three different data models. For each data model, we explore the performance of representative Text-to-SQL systems and language models. We further quantify the impact of training data size, pre-, and post-processing steps as well as language model inference time. Our comprehensive evaluation sheds light on the design choices of real-world Text-to-SQL systems and their impact on moving from research prototypes to real deployments. Last, we provide a new benchmark dataset to the community, which is the first to enable the evaluation of different data models for the same dataset and is substantially more challenging than most previous datasets in terms of query complexity.

Bin Cheng, Jonathan Fürst, Tobias Jacobs et al.

The creation of high-quality ontologies is crucial for data integration and knowledge-based reasoning, specifically in the context of the rising data economy. However, automatic ontology matchers are often bound to the heuristics they are based on, leaving many matches unidentified. Interactive ontology matching systems involving human experts have been introduced, but they do not solve the fundamental issue of flexibly finding additional matches outside the scope of the implemented heuristics, even though this is highly demanded in industrial settings. Active machine learning methods appear to be a promising path towards a flexible interactive ontology matcher. However, off-the-shelf active learning mechanisms suffer from low query efficiency due to extreme class imbalance, resulting in a last-mile problem where high human effort is required to identify the remaining matches. To address the last-mile problem, this work introduces DualLoop, an active learning method tailored to ontology matching. DualLoop offers three main contributions: (1) an ensemble of tunable heuristic matchers, (2) a short-term learner with a novel query strategy adapted to highly imbalanced data, and (3) long-term learners to explore potential matches by creating and tuning new heuristics. We evaluated DualLoop on three datasets of varying sizes and domains. Compared to existing active learning methods, we consistently achieved better F1 scores and recall, reducing the expected query cost spent on finding 90% of all matches by over 50%. Compared to traditional interactive ontology matchers, we are able to find additional, last-mile matches. Finally, we detail the successful deployment of our approach within an actual product and report its operational performance results within the Architecture, Engineering, and Construction (AEC) industry sector, showcasing its practical value and efficiency.

Daniel Huwiler, Kurt Stockinger, Jonathan Fürst

Retrieval-Augmented Generation (RAG) systems fail when documents evolve through versioning-a ubiquitous characteristic of technical documentation. Existing approaches achieve only 58-64% accuracy on version-sensitive questions, retrieving semantically similar content without temporal validity checks. We present VersionRAG, a version-aware RAG framework that explicitly models document evolution through a hierarchical graph structure capturing version sequences, content boundaries, and changes between document states. During retrieval, VersionRAG routes queries through specialized paths based on intent classification, enabling precise version-aware filtering and change tracking. On our VersionQA benchmark-100 manually curated questions across 34 versioned technical documents-VersionRAG achieves 90% accuracy, outperforming naive RAG (58%) and GraphRAG (64%). VersionRAG reaches 60% accuracy on implicit change detection where baselines fail (0-10%), demonstrating its ability to track undocumented modifications. Additionally, VersionRAG requires 97% fewer tokens during indexing than GraphRAG, making it practical for large-scale deployment. Our work establishes versioned document QA as a distinct task and provides both a solution and benchmark for future research.

Chenyue Zhou, Gürkan Solmaz, Flavio Cirillo et al.

Humanitarian Mine Action (HMA) addresses the challenge of detecting and removing landmines from conflict regions. Much of the life-saving operational knowledge produced by HMA agencies is buried in unstructured reports, limiting the transferability of information between agencies. To address this issue, we propose TextMine: the first dataset, evaluation framework and ontology-guided large language model (LLM) pipeline for knowledge extraction in the HMA domain. TextMine structures HMA reports into (subject, relation, object)-triples, thus creating domain-specific knowledge. To ensure real-world relevance, we created the dataset in collaboration with Cambodian Mine Action Center (CMAC). We further introduce a bias-aware evaluation framework that combines human-annotated triples with an LLM-as-Judge protocol to mitigate position bias in reference-free scoring. Our experiments show that ontology-aligned prompts improve extraction accuracy by up to 44.2%, reduce hallucinations by 22.5%, and enhance format adherence by 20.9% compared to baseline models. We publicly release the dataset and code.

Gaye Colakoglu, Gürkan Solmaz, Jonathan Fürst

Declaration of Performance (DoP) documents, mandated by EU regulation, certify the performance of construction products. There are two challenges to make DoPs machine and human accessible through automated key-value pair extraction (KVP) and question answering (QA): (1) While some of their content is standardized, DoPs vary widely in layout, schema, and format; (2) Both users and documents are multilingual. Existing static or LLM-only Information Extraction (IE) pipelines fail to adapt to this structural document and user diversity. Our domain-specific, agentic system addresses these challenges through a planner-executor-responder architecture. The system infers user intent, detects document language and modality, and orchestrates tools dynamically for robust, traceable reasoning while avoiding tool misuse or execution loops. Our agent outperforms baselines (ROUGE: 0.783 vs. 0.703/0.608) with better cross-lingual stability (17-point vs. 21-26-point variation).