Papers by Matthias Orlikowski
Personalization up to a Point: Why Personalized Content Moderation Needs Boundaries, and How We Can Enforce Them (2025.emnlp-main)
Copied to clipboard
| Challenge: | Personalized content moderation can protect users from harm while facilitating free expression . however, it can also allow highly harmful and even illegal hate speech to spread . |
| Approach: | They propose to enforce legal boundaries on personalized content moderation models to reduce legal violations while maintaining user welfare. |
| Outcome: | The proposed approach reduces legal violations while maintaining user welfare while maintaining a high degree of model performance. |
The Ecological Fallacy in Annotation: Modeling Human Label Variation goes beyond Sociodemographics (2023.acl-short)
Copied to clipboard
| Challenge: | Existing work has attempted to model individual annotation behaviour rather than predicting aggregated labels. |
| Approach: | They propose to model individual annotator behaviour rather than predicting aggregated labels by adding group-specific layers to multi-annotator models to account for sociodemographics. |
| Outcome: | The proposed model does not significantly improve on toxic content detection tasks. |
Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It’s Best to Relate Perspectives! (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to subjectivity in natural language processing are subjective . authors argue that disagreement should not be regarded as a problem . |
| Approach: | They propose to account for subjective perspectives of individuals and objective concepts that build a common ground between annotators. |
| Outcome: | The proposed architectures increase the averaged annotator-individual F1-scores up to 43% over a majority-label model. |
Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals’ Subjective Text Perceptions (2025.acl-long)
Copied to clipboard
| Challenge: | Recent work has shown that LLMs perform poorly when prompted with sociodemographic attributes, suggesting limited inherent sociodemography knowledge. |
| Approach: | They propose to train large language models to be accurate sociodemographic models of annotator variation by using a curated dataset of five tasks with standardized sociodemography. |
| Outcome: | The proposed models improve in sociodemographic prompting when trained but this performance gain is largely due to models learning annotator-specific behaviour rather than sociodemography. |