5 citations · 13 across the 11 of their papers we have counts for
4 papers · 2 filters
HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter
Manuel Tonneau, Diyi Liu, Niyati Malhotra +4
To address the global challenge of online hate speech, prior research has developed detection models to flag such content on social media. However, due to systematic biases in eval…
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
Xinpeng Wang, Chengzhi Hu, Paul Röttger +1
Training a language model to be both helpful and harmless requires careful calibration of refusal behaviours: Models should refuse to follow malicious instructions or give harmful…
From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets
Manuel Tonneau, Diyi Liu, Samuel Fraiberger +3
Perceptions of hate can vary greatly across cultural contexts. Hate speech (HS) datasets, however, have traditionally been developed by language. This hides potential cultural bias…
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
Hannah Rose Kirk, Alexander Whitefield, Paul Röttger +9
Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains (where), people (who) and objectives (to wha…