Seminars - page 2
The DIG team holds a seminar about every two weeks with speakers either from the team, or invited.
You can add the seminars to your calendar with this ics file, and get emails about future seminars by subscribing to our mailing-list.
If you would like to present your work at our seminar, please contact Nils.
Upcoming Seminars
Towards Conflict-Aware LLM Reasoning Grounded in Open Multilingual Knowledge Graphs
Tuesday, September 08, 2026 11:45, 4A301
Laura Balbi (University of Lisbon)
Large Language Models (LLMs) increasingly operate in settings where they must reason over heterogeneous sources of knowledgecontaining ambiguities and conflicts whose detection and interpretation requires implicit semantic understanding. Knowledge graphs provide a structured and formally defined representation of such knowledge, making them particularly valuable for studying and supporting these reasoning processes. My research investigates how well LLM-based systems detect and reason over conflicts grounded in formal knowledge graph semantics.
Structured Clinical Reasoning with Foundation Models
Tuesday, September 15, 2026 11:45, 4A301
Zhan Qu (Scads Dresden)
Foundation models have demonstrated strong capabilities across a wide range of clinical tasks, yet their application to longitudinal electronic health records (EHRs) remains limited by the difficulty of evaluating clinically grounded reasoning, maintaining consistent patient-state representations over time, and predicting future clinical events within large, weakly structured outcome spaces. My research addresses these challenges by introducing structured methods for clinical AI across evaluation, inference, and prediction. I develop an ontology-grounded evaluation framework that jointly assesses factual correctness and patient-contextual grounding, enabling systematic identification of clinically meaningful reasoning errors beyond conventional accuracy metrics. I further investigate protocol-constrained longitudinal reasoning through persistent patient-state representations that evolve with incoming clinical evidence, improving temporal consistency, calibration, and interpretability over extended patient trajectories. Finally, I reformulate longitudinal prediction as reasoning within structured hypothesis spaces by combining medical coding hierarchies with data-driven temporal and cross-modal associations to construct patient-specific candidate outcomes before inference. Together, these studies demonstrate how explicit clinical structure can be incorporated throughout the clinical AI pipeline, integrating biomedical knowledge, longitudinal patient states, and structured hypothesis spaces to improve the reliability, interpretability, and clinical grounding of foundation models for longitudinal decision support.
Past Seminars
Contextual knowledge representation for neurosymbolic Artificial Intelligence reasoning
Thursday, December 11, 2025 12:15, 4A301
Simon Coumes
The field of Knowledge Representation and Reasoning is concerned with the representation of information about reality in a form that is both human-readable and machine-processable. It has been a part of artificial intelligence since its inception, and has produced many important formalisms and systems. One key aspect of knowledge is the context in which it is expressed. This has been identified early on in the field and matches with our common experience: understanding a statement or judging its validity often require to know in what context it was meant. Historically, there has been some work aiming at producing logics implementing a general notion of context. None of them saw a lot of adoption, in part because they lack either sufficient expressive power or because they were not sufficiently usable.
SPECTRA: Faster Large Language Model Inference with Optimized Internal and External Speculation
Tuesday, December 09, 2025 11:45, 1D19
Le-Minh Nguyen (Japan Advanced Institute of Science and Technology)
Inference with modern Large Language Models (LLMs) is both computationally intensive and time-consuming. While speculative decoding has emerged as a promising solution, existing approaches face key limitations. Training-based methods require the development of a draft model, which is often difficult to obtain and lacks generalizability. On the other hand, training-free methods provide only modest speedup improvements. In this work, we introduce SPECTRA — a novel framework designed to accelerate LLM inference without requiring any additional training or modifications to the original LLM. SPECTRA incorporates two new techniques that efficiently leverage both internal and external speculation, each independently outperforming corresponding state-of-the-art (SOTA) methods. When combined, these techniques deliver up to a 4.08× speedup across a variety of benchmarks and LLM architectures, significantly surpassing existing training-free approaches. The implementation of SPECTRA is publicly available. Biography: Le-Minh Nguyen is currently a Professor of the School of Information Science and the director of the Interpretable AI Center at JAIST. He leads the Machine Learning and Natural Language Understanding Laboratory at JAIST. He is currently taking his sabbatical at Imperial College London, UK (Until April 2026). His research interests include machine learning & deep learning, natural language processing, legal text processing, and explainable AI. He serves as an action editor of TACL (a leading journal in NLP), a board member of VLSP (Vietnamese language and speech processing), and an editorial board member of AI &Law, Journal of Natural Language Processing (Cambridge). He is a steering committee of Juris-informatics (Jurisin) in Japan – a research area that studies legal issues from informatics.
Mining Expressive Cross-Table Dependencies in Relational Databases
Tuesday, December 02, 2025 11:45, 4A125
François Amat
This thesis addresses the gap between what relational database schemas declare and the richer set of cross-table rules that actually govern real-world data. It introduces MATILDA, the first deterministic system capable of mining expressive first-order tuple-generating dependencies (FO-TGDs) with multi-atom heads, existential witnesses, and recursion directly from arbitrary relational databases, using principled, database-native definitions of support and confidence. MATILDA uncovers hidden business rules, workflow constraints, and multi-relation regularities that schemas alone cannot capture, while ensuring reproducible results through canonicalized search and tractable pruning guided by a constraint graph. To understand when simpler formalisms suffice, the thesis also presents MAHILDA, a relational Horn-rule baseline equipped with disjoint semantics to prevent self-justifying recursion. Overall, the work shows that expressive rule mining on realistic databases is both feasible and insightful, enabling more systematic, explainable, and schema-grounded analyses of complex relational data.
Entity Linking and Relation Extraction for Historical Italian Texts: Challenges and Potential Solutions
Tuesday, October 28, 2025 11:45, 4A125
Cristian Santini (University of Macerata)
Entity Linking and Relation Extraction enable the automatic identification of named entities mentioned in texts, along with their relationships, by connecting them to external knowledge graphs such as Wikidata. While these techniques work well on modern documents, applying them to historical texts presents significant challenges due to the diachronic evolution of language and limited resources for training computational models. This seminar presents recent work on developing methods and datasets for processing historical Italian texts. It will discuss the creation of a new benchmark dataset extracted from digital scholarly editions covering two centuries of Italian literary and political writing. The talk will then present approaches that enhance entity disambiguation by incorporating temporal and contextual information from external Wikidata. Finally, it will detail a method for automatically constructing knowledge graphs from historical correspondence that combines multiple language models in sequence, demonstrating how these technologies can facilitate the exploration and understanding of historical archives without requiring extensive manual annotation or model training.
FLORA: Unsupervised Knowledge Graph Alignment by Fuzzy Logic
Tuesday, October 21, 2025 11:45, 4A301
Yiwen Peng & Fabian Suchanek
Knowledge graph alignment is the task of matching equivalent entities (that is, instances and classes) and relations across two knowledge graphs. Most existing methods focus on pure entity-level alignment, computing the similarity of entities in some embedding space. They lack interpretable reasoning and need training data to work. To solve these issues, we introduce FLORA, a simple yet effective method that (1) is unsupervised, i.e., does not require training data, (2) provides a holistic alignment for entities and relations iteratively, (3) is based on fuzzy logic and thus delivers interpretable results, (4) provably converges, (5) allows dangling entities, i.e., entities without a counterpart in the other KG, and (6) achieves state-of-the-art results on major benchmarks.
Data- and knowledge-driven approaches for step-by-step guidance to differential diagnosis
Tuesday, October 07, 2025 11:45, 4A301
Adrien Coulet (INRIA)
Diagnosis guidelines provide recommendations based on expert consensus that cover the majority of the population, but often overlook patients with uncommon conditions or multiple morbidities. We will present and compare two alternative approaches that provide a step-by-step guidance to the differential diagnosis of anemia and lupus. The first approach relies on reinforcement learning and observational data. The second on large langage models and domain knowledge.
Meaning Representations and Reasoning in the Age of Large Language Models
Tuesday, September 30, 2025 11:45, 3A301
Zacchary Sadeddine
This thesis explores how to make large language models (LLMs) more reliable and transparent in their reasoning. It first examines around fifteen societal issues related to these models, such as disinformation or user overreliance, and then investigates symbolic structures from linguistics and how they can be used to improve the performance and transparency of LLMs. It presents VANESSA, a reasoning neuro-symbolic system that combines the power of neural models with the rigor of symbolic reasoning, achieving performance comparable to LLMs while remaining transparent. Finally, it addresses the problem of verifying LLM outputs by introducing a step-by-step verification benchmark, paving the way for more interpretable, controllable and trustworthy artificial intelligence systems.
Robust Knowledge Graph Cleaning
Tuesday, May 27, 2025 11:45, 4A301
Maximilian Egger
Data quality is needed to properly and reliably use the information represented in the dataset. The increasing volume of data renders data preparation and cleaning increasingly difficult. Additionally, more diverse types of data structures for databases, like graphs, get used and need to be handled differently. This leads to the necessity of robust methods to increase data integrity, scalable approaches for finding and fixing errors, and local-oriented algorithms that can be used to pinpoint attention where needed.
Synthesis & Augmentation of Tabular Data In the Age of Foundation Models
Tuesday, May 13, 2025 11:45, 4A301
Nikola Simidjievski
Foundation models - large pre-trained performant models - have shown remarkable success in applications that predominately focus on vision, language, and sound data. On the other hand, tabular data - one of the most prevalent data modalities in many critical domains of business, science, and healthcare - has seen limited benefits from these advances. Tabular data poses unique challenges that relate to heterogeneity, dimensionality, and scarcity as well as lack of explicit symmetries, implicit structures and incomplete prior knowledge – all of which have limiting effects on how we construct, train and apply/transfer large models for tabular data.
GPTKB: Comprehensively Materializing Factual LLM Knowledge
Tuesday, April 29, 2025 11:45, 4A301
Simon Razniewski (TU Dresden)
LLMs have majorly advanced NLP and AI, and next to their ability to perform a wide range of procedural tasks, a major success factor is their internalized factual knowledge. Since (Petroni et al., 2019), analyzing this knowledge has gained attention. However, most approaches investigate one question at a time via modest-sized pre-defined samples, introducing an “availability bias” (Tversky and Kahneman, 1973) that prevents the discovery of knowledge (or beliefs) of LLMs beyond the experimenter’s predisposition. To address this challenge, we propose a novel methodology to comprehensively materialize an LLM’s factual knowledge through recursive querying and result consolidation. As a prototype, we employ GPT-4o-mini to construct GPTKB, a large-scale knowledge base (KB) comprising 101 million triples for over 2.9 million entities. This work marks a milestone in two areas: For LLM research, for the first time, it provides constructive insights into the scope and structure of LLMs’ knowledge (or beliefs), and its strengths and weaknesses. For KB construction, it pioneers new pathways for the long-standing challenge of general-domain KB construction. GPTKB is accessible at https://gptkb.org.