5 citations · 13 across the 11 of their papers we have counts for
11 papers
The Enforcement and Feasibility of Hate Speech Moderation
Manuel Tonneau, Dylan Thurgood, Diyi Liu +7
Online hate speech is associated with harms ranging from deteriorating mental health to violence, yet how consistently platforms moderate hate, and whether enforcement is feasible…
SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
Tiancheng Hu, Joachim Baumann, Lorenzo Lupo +3
Large language model (LLM) simulations of human behavior have the potential to revolutionize the social and behavioral sciences, if and only if they faithfully reflect real human b…
Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance
Pedro Henrique Luz de Araujo, Paul Röttger, Dirk Hovy +1
Expert persona prompting -- assigning roles such as expert in math to language models -- is widely used for task improvement. However, prior work shows mixed results on its effecti…
Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions
Matthias Orlikowski, Jiaxin Pei, Paul Röttger +3
People naturally vary in their annotations for subjective questions and some of this variation is thought to be due to the person's sociodemographic characteristics. LLMs have also…
Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations
Yong Cao, Haijiang Liu, Arnav Arora +3
Large-scale surveys are essential tools for informing social science research and policy, but running surveys is costly and time-intensive. If we could accurately simulate group-le…
AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages
Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Abinew Ali Ayele +24
Hate speech and abusive language are global phenomena that need socio-cultural background knowledge to be understood, identified, and moderated. However, in many regions of the Glo…
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…
Near to Mid-term Risks and Opportunities of Open-Source Generative AI
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +21
In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for thes…
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…