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.

We analyze the type of learned optimization that occurs when a learned model (such as a neural network) is itself an optimizer-a situation we refer to as mesa-optimization, a neologism we introduce in this paper. We believe that the possibility of mesa-optimization raises two important questions for the safety and transparency of advanced machine learning systems. First, under what circumstances will learned models be optimizers, including when they should not be? Second, when a learned model is an optimizer, what will its objective be-how will it differ from the loss function it was trained under-and how can it be aligned? In this paper, we provide an in-depth analysis of these two primary questions and provide an overview of topics for future research.

Recent large language models often answer factual questions correctly. But users can't trust any given claim a model makes without fact-checking, because language models can hallucinate convincing nonsense. In this work we use reinforcement learning from human preferences (RLHP) to train "open-book" QA models that generate answers whilst also citing specific evidence for their claims, which aids in the appraisal of correctness. Supporting evidence is drawn from multiple documents found via a search engine, or from a single user-provided document. Our 280 billion parameter model, GopherCite, is able to produce answers with high quality supporting evidence and abstain from answering when unsure. We measure the performance of GopherCite by conducting human evaluation of answers to questions in a subset of the NaturalQuestions and ELI5 datasets. The model's response is found to be high-quality 80% of the time on this Natural Questions subset, and 67% of the time on the ELI5 subset. Abstaining from the third of questions for which it is most unsure improves performance to 90% and 80% respectively, approaching human baselines. However, analysis on the adversarial TruthfulQA dataset shows why citation is only one part of an overall strategy for safety and trustworthiness: not all claims supported by evidence are true.

Understanding the inductive bias of neural networks is critical to explaining their ability to generalise. Here, for one of the simplest neural networks -a single-layer perceptron with n input neurons, one output neuron, and no threshold bias termwe prove that upon random initialisation of weights, the a priori probability P (t) that it represents a Boolean function that classifies t points in {0, 1} n as 1 has a remarkably simple form: P (t) = 2 −n for 0 ≤ t < 2 n . Since a perceptron can express far fewer Boolean functions with small or large values of t (low "entropy") than with intermediate values of t (high "entropy") there is, on average, a strong intrinsic a-priori bias towards individual functions with low entropy. Furthermore, within a class of functions with fixed t, we often observe a further intrinsic bias towards functions of lower complexity. Finally, we prove that, regardless of the distribution of inputs, the bias towards low entropy becomes monotonically stronger upon adding ReLU layers, and empirically show that increasing the variance of the bias term has a similar effect.

DeepMind, * Work done at DeepMind. Interpretability research aims to build tools for understanding machine learning (ML) models. However, such tools are inherently hard to evaluate because we do not have ground truth information about how ML models actually work. In this work, we propose to build transformer models manually as a testbed for interpretability research. We introduce Tracr, a "compiler" for translating human-readable programs into weights of a transformer model. Tracr takes code written in RASP, a domain-specific language (Weiss et al., 2021), and translates it into weights for a standard, decoder-only, GPT-like transformer architecture. We use Tracr to create a range of ground truth transformers that implement programs including computing token frequencies, sorting, and Dyck-n parenthesis checking, among others. We study the resulting models and discuss how this approach can accelerate interpretability research. To enable the broader research community to explore and use compiled models, we provide an open-source implementation of Tracr at https://github.com/deepmind/tracr.