Papers by Alexander Löser
CliniBench: A Clinical Outcome Prediction Benchmark for Generative and Encoder-Based Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | generative large language models are being investigated for complex medical tasks, but their effectiveness in real-world clinical applications remains underexplored. |
| Approach: | They propose to compare encoder-based classifiers and generative LLMs for discharge diagnosis prediction from admission notes in a MIMIC-IV dataset. |
| Outcome: | The proposed benchmark compares encoder-based classifiers and generative LLMs for discharge diagnosis prediction from admission notes in the MIMIC-IV dataset. |
KIMERA: Injecting Domain Knowledge into Vacant Transformer Heads (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent studies show that transformer models lack specific domain knowledge and are under-performing in broad domains like the medical domain. |
| Approach: | They propose a method for retraining and instilling attention heads with structured domain knowledge by masking redundant attention heads. |
| Outcome: | The proposed method improves on seven datasets in the medical domain in information retrieval and clinical outcome prediction settings. |
Attention Networks for Augmenting Clinical Text with Support Sets for Diagnosis Prediction (2022.coling-1)
Copied to clipboard
| Challenge: | Clinical language models may suffer from imbalanced vocabulary for describing diseases or symptoms. |
| Approach: | They propose to augment clinical text with potentially complementary diagnostic codes from prior admissions or as they emerge during differential diagnosis to improve the performance. |
| Outcome: | The proposed approach outperforms the previous state-of-the-art PubMedBERT by up 3% points. |
TrainX – Named Entity Linking with Active Sampling and Bi-Encoders (2020.coling-demos)
Copied to clipboard
Tom Oberhauser, Tim Bischoff, Karl Brendel, Maluna Menke, Tobias Klatt, Amy Siu, Felix Alexander Gers, Alexander Löser
| Challenge: | Existing easyto-use annotation tools do not support entity linking, which leads to additional training costs for medical professionals. |
| Approach: | They propose a system for Named Entity Linking for medical experts . they use Flair and BERT to support annotating training data with active sampling . |
| Outcome: | The proposed system is capable of linking against large knowledge bases and supporting zero-shot cases where the linker has never seen the entity before. |
Discovering Biased News Articles Leveraging Multiple Human Annotations (2020.lrec-1)
Copied to clipboard
| Challenge: | Political propaganda and one-sided views can be found in the news and can cause distrust in media. |
| Approach: | They propose to annotate politically biased news articles by an algorithm annotated by domain experts and crowd workers and to compare them to crowd workers. |
| Outcome: | The proposed method compares domain experts to crowd workers and shows that bias can be detected automatically. |