Publications

Retrieval-augmented generation (RAG) helps address the limitations of the parametric knowledge embedded within a language model (LM). However, investigations of how LMs utilise retrieved information of varying complexity in real-world scenarios have been limited to synthetic contexts. We introduce DRUID (Dataset of Retrieved Unreliable, Insufficient and Difficult-to-understand contexts) with real-world... [Read More]

Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge. However, conflicting knowledge can be present in the LM’s parameters, termed intra-memory conflict, which can affect a model’s propensity to accept contextual knowledge. To study the effect of... [Read More]

Explainable AI methods facilitate the understanding of model behaviour, yet, small, imperceptible perturbations to inputs can vastly distort explanations. As these explanations are typically evaluated holistically, before model deployment, it is difficult to assess when a particular explanation is trustworthy. Some studies have tried to create confidence estimators for explanations,... [Read More]

Despite attempts to increase gender parity in politics, global efforts have struggled to ensure equal female representation. This is likely tied to implicit gender biases against women in authority. In this work, we present a comprehensive study of gender biases that appear in online political discussion. To this end, we... [Read More]

We study how citizens engage with misinformation on Twitter in Denmark during the COVID-19 pandemic. We find that misinformation regarding facemasks is not corrected through counterarguments or fact-checking. Instead, many tweets rejecting misinformation use humor to mock misinformation spreaders, whom they pejoratively label wearers of “tinfoil hats.” Tweets rejecting misinformation... [Read More]