7 papers
BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Elicitation
Sekh Mainul Islam, Nadav Borenstein, Siddhesh Milind Pawar +3
Understanding biases and stereotypes encoded in the weights of Large Language Models (LLMs) is crucial for developing effective mitigation strategies. However, biased behaviour is…
Revealing Fine-Grained Values and Opinions in Large Language Models
Dustin Wright, Arnav Arora, Nadav Borenstein +3
Uncovering latent values and opinions embedded in large language models (LLMs) can help identify biases and mitigate potential harm. Recently, this has been approached by prompting…
Investigating Human Values in Online Communities
Nadav Borenstein, Arnav Arora, Lucie-Aimée Kaffee +1
Studying human values is instrumental for cross-cultural research, enabling a better understanding of preferences and behaviour of society at large and communities therein. To stud…
Can Community Notes Replace Professional Fact-Checkers?
Nadav Borenstein, Greta Warren, Desmond Elliott +1
Two commonly employed strategies to combat the rise of misinformation on social media are (i) fact-checking by professional organisations and (ii) community moderation by platform…
Revisiting Noise in Natural Language Processing for Computational Social Science
Nadav Borenstein
Computational Social Science (CSS) is an emerging field driven by the unprecedented availability of human-generated content for researchers. This field, however, presents a unique…
What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages
Nadav Borenstein, Anej Svete, Robin Chan +5
What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formali…