9607 research outputs found
Sort by
Code Like Humans: A Multi-Agent Solution for Medical Coding
No full textIn medical coding, experts map unstructured clinical notes to alphanumeric codes for diagnoses and procedures. We introduce `Code Like Humans': a new agentic framework for medical coding with large language models. It implements official coding guidelines for human experts, and it is the first solution that can support the full ICD-10 coding system (+70K labels). It achieves the best performance to date on rare diagnosis codes. Fine-tuned discriminative classifiers retain an advantage for high-frequency codes, to which they are limited. Towards future work, we also contribute an analysis of system performance and identify its `blind spots' (codes that are systematically undercoded)
High-dimensional density-based clustering using locality-sensitive hashing
No full textThe DBSCAN algorithm is a popular density-based clustering method to find clusters of arbitrary shapes without requiring an initial guess on the number of clusters. While there are methods to run DBSCAN efficiently in low-dimensional data in near-linear time, there remains a need for an efficient DBSCAN algorithm that scales to high-dimensional data. The bottleneck in highdimensional data is that the range queries necessary in carrying out the algorithm suffer from the curse of dimensionality. In this paper we present the SRRDBSCAN algorithm. This algorithm is an implementation of approximate DBSCAN using locality-sensitive hashing. We prove sub-quadratic running time bounds under reasonable assumptions about the data. An important ingredient in the design of the data structure is the use of a multi-level LSH data structure, which automatically adapts to the density of data points. An extensive empirical analysis shows that the approximation does not significantly impact the quality of the clustering found by the algorithm as compared to the exact DBSCAN clustering. Moreover, our algorithm is competitive with other approaches even in low-dimensional settings, and thus provides a general-purpose DBSCAN implementation for arbitrary data
Homomorphism Tensors and Linear Equations
No full textLovász (1967) showed that two graphs and are isomorphic if and only ifthey are homomorphism indistinguishable over the class of all graphs, i.e. for every graph , the number of homomorphisms from to equals the number of homomorphisms from to . Recently, homomorphism indistinguishability over restricted classes of graphs such as bounded treewidth, bounded treedepth and planar graphs, has emerged as a surprisingly powerful framework for capturing diverse equivalence relations on graphs arising from logical equivalence and algebraic equation systems.In this paper, we provide a unified algebraic framework for such results by examining the linear-algebraic structure of tensors counting homomorphisms from labelled graphs. The existence of certain linear transformations between such homomorphism tensor subspaces can be interpreted both as homomorphism indistinguishability over a graph class and as feasibility of an equational system. Following this framework, we obtain characterisations of homomorphism indistinguishability over several natural graph classes, namely trees of bounded degree, graphs of bounded pathwidth (answering a question of Dell et al. (2018)), and graphs of bounded treedepth
Disabled ecologies:lessons from a conceptually armed study of disability, aquifers, and state-industrial harm
No full textSnakModel: Lessons Learned from Training an Open Danish Large Language Model
No full textWe present SnakModel, a Danish large language model (LLM) based on Llama2-7B, which we continuously pre-train on 13.6B Danish words, and further tune on 3.7M Danish instructions. As best practices for creating LLMs for smaller language communities have yet to be established, we examine the effects of early modeling and training decisions on downstream performance throughout the entire training pipeline, including (1) the creation of a strictly curated corpus of Danish text from diverse sources; (2) the language modeling and instruction-tuning training process itself, including the analysis of intermediate training dynamics, and ablations across different hyperparameters; (3) an evaluation on eight language and culturally-specific tasks. Across these experiments SnakModel achieves the highest overall performance, outperforming multiple contemporary Llama2-7B-based models. By making SnakModel, the majority of our pre-training corpus, and the associated code available under open licenses, we hope to foster further research and development in Danish Natural Language Processing, and establish training guidelines for languages with similar resource constraints
DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers
No full textLarge Language Models (LLMs) have seen widespread societal adoption. However, while they are able to interact with users in languages beyond English, they have been shown to lack cultural awareness, providing anglocentric or inappropriate responses for underrepresented language communities. To investigate this gap and disentangle linguistic versus cultural proficiency, we conduct the first cultural evaluation study for the mid-resource language of Danish, in which native speakers prompt different models to solve tasks requiring cultural awareness. Our analysis of the resulting 1,038 interactions from 63 demographically diverse participants highlights open challenges to cultural adaptation: Particularly, how currently employed automatically translated data are insufficient to train or measure cultural adaptation, and how training on native-speaker data can more than double response acceptance rates. We release our study data as DaKultur - the first native Danish cultural awareness dataset
When the Place of Care Is Hybrid: An Ethnographic Study of Hospital Video Consultations
No full textBased on ethnographic observations of hospital video consultations between clinicians and patients, this article investigates the shifting places of care when consultations are displaced from the clinic. While information and communication technologies allow care across distance, scholars within science and technology studies (STS) and sociology have demonstrated how places still matter to the delivery of healthcare services. However, as healthcare increasingly enters the digital realm, we need a vocabulary and analytics which also address virtual environments' constitutive effects as places of care. This article argues that place must be understood as more than the locations of the consulting parties and be expanded to include the virtual places created during video consultations. Drawing on insights from STS and computer-supported cooperative work, the concept of hybrid place is proposed to capture the spatial hybridity of video consultations when physical locations are virtually connected and projected into virtual environments. The concept becomes a useful heuristic for understanding the spatial reconfiguration of the place of care during video consultations; it brings attention to the multiplicity of places, their connections and their distinct conditions which co-shape the virtual clinical encounter.Based on ethnographic observations of hospital video consultations between clinicians and patients, this article investigates the shifting places of care when consultations are displaced from the clinic. While information and communication technologies allow care across distance, scholars within science and technology studies (STS) and sociology have demonstrated how places still matter to the delivery of healthcare services. However, as healthcare increasingly enters the digital realm, we need a vo-cabulary and analytics which also address virtual environments' constitutive effects as places of care. This article argues that place must be understood as more than the locations of the consulting parties and be expanded to include the virtual places created during video consultations. Drawing on insights from STS and computer-supported cooperative work, the concept of hybrid place is proposed to capture the spatial hybridity of video consultations when physical locations are virtually connected and projected into virtual environments. The concept becomes a useful heuristic for understanding the spatial reconfiguration of the place of care during video consultations; it brings attention to the multiplicity of places, their connections and their distinct conditions which co-shape the virtual clinical encounter
Re-Imagining the Landscape of Future Farming
Get PDFThis paper explores how participatory design methods can engage future farmers in imagining sustainable agricultural futures in Denmark. Denmark's agricultural sector faces a "crisis of imagination" where dominant paradigms in farming are hard to challenge. Building on Ingold's notion of the landscape as a relational, temporal space for dwelling, we propose a conceptualization of the landscape game that enables farming students to articulate their visions of future farming. The design game creates opportunities for participants to situate their imagined farms within broader social, environmental, and technical contexts while exploring how these might evolve over time. This approach aims to generate new agricultural imaginaries that move beyond current techno-solutionist or radical transformation narratives, while supporting an underrepresented political public in developing their own perspective on contested agricultural futures that are both speculative and grounded in lived experience
AntiCheatPT: A Transformer-Based Approach to Cheat Detection in Competitive Computer Games
No full textCheating in online video games compromises the integrity of gaming experiences. Anti-cheat systems, such as VAC (Valve Anti-Cheat), face significant challenges in keeping pace with evolving cheating methods without imposing invasive measures on users' systems. This paper presents AntiCheatPT_256, a transformer-based machine learning model designed to detect cheating behaviour in Counter-Strike 2 using gameplay data. To support this, we introduce and publicly release CS2CD: A labelled dataset of 795 matches. Using this dataset, 90,707 context windows were created and subsequently augmented to address class imbalance. The transformer model, trained on these windows, achieved an accuracy of 89.17% and an AUC of 93.36% on an unaugmented test set. This approach emphasizes reproducibility and real-world applicability, offering a robust baseline for future research in data-driven cheat detection
Findings of the VarDial Evaluation Campaign 2025: The NorSID Shared Task on Norwegian Slot, Intent and Dialect Identification
No full textThe VarDial Evaluation Campaign 2025 was organized as part of the twelfth workshop on Natural Language Processing for Similar Languages, Varieties and Dialects (VarDial), colocated with COLING 2025. It consisted of one shared task with three subtasks: intent detection, slot filling and dialect identification for Norwegian dialects. This report presents the results of this shared task. Four participating teams have submitted systems with very high performance (> 97% accuracy) for intent detection, whereas slot detection and dialect identification showed to be much more challenging, with respectively span-F1 scores up to 89%, and weighted dialect F1 scores of 84%