23 citations · 77 across the 11 of their papers we have counts for
11 papers
Do Multilingual LLMs Think In English?
Lisa Schut, Yarin Gal, Sebastian Farquhar
Large language models (LLMs) have multilingual capabilities and can solve tasks across various languages. However, we show that current LLMs make key decisions in a representation…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1167
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
Jannik Kossen, Jiatong Han, Muhammed Razzak +3
We propose semantic entropy probes (SEPs), a cheap and reliable method for uncertainty quantification in Large Language Models (LLMs). Hallucinations, which are plausible-sounding…
Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors
Angus Nicolson, Lisa Schut, J. Alison Noble +1
Concept-based explanations translate the internal representations of deep learning models into a language that humans are familiar with: concepts. One popular method for finding co…
Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero
Lisa Schut, Nenad Tomasev, Tom McGrath +3
Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains. This presents us with an opportunity to further human…
Diversifying AI: Towards Creative Chess with AlphaZero
Tom Zahavy, Vivek Veeriah, Shaobo Hou +7
In recent years, Artificial Intelligence (AI) systems have surpassed human intelligence in a variety of computational tasks. However, AI systems, like humans, make mistakes, have b…