Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms.

No abstract

This paper aims to help structure the risk landscape associated with large-scale Language Models (LMs). In order to foster advances in responsible innovation, an in-depth understanding of the potential risks posed by these models is needed. A wide range of established and anticipated risks are analysed in detail, drawing on multidisciplinary literature from computer science, linguistics, and social sciences.

Humans are extremely susceptible to social influence. Here, we examine whether this susceptibility is altered in autism, a condition characterized by social difficulties. Autistic participants (N = 22) and neurotypical controls (N = 22) completed a memory test of previously seen words and were then exposed to answers supposedly given by four other individuals. Autistic individuals and controls were as likely to alter their judgements to align with inaccurate responses of group members. These changes reflected both temporary judgement changes (public conformity) and long-lasting memory changes (private conformity). Both groups were more susceptible to answers believed to be from other humans than from computer algorithms. Our results suggest that autistic individuals and controls are equally susceptible to social influence when reporting their memories.