Ambrose Slone
Authored Publications
Sort By
Solving Quantitative Reasoning Problems with Language Models
Aitor Lewkowycz
David Martin Dohan
Ethan S Dyer
Henryk Michalewski
Cem Anil
Imanol Schlag
Theo Gutman-Solo
Yuhuai Wu
Behnam Neyshabur
Guy Gur-Ari
NeurIPS (2022)
Preview abstract
Language models have achieved remarkable performance on a wide range of tasks that require natural language understanding. Nevertheless, state-of-the-art models have generally struggled with tasks that require quantitative reasoning, such as solving mathematics, science, and engineering problems at the college level. To help close this gap, we introduce Minerva, a large language model pretrained on general natural language data and further trained on technical content. The model achieves state-of-the-art performance on technical benchmarks without the use of external tools. We also evaluate our model on over two hundred undergraduate-level problems in physics, biology, chemistry, economics, and other sciences that require quantitative reasoning, and find that the model can correctly answer nearly a third of them.
View details
Exploring Length Generalization in Large Language Models
Cem Anil
Yuhuai Wu
Aitor Lewkowycz
Guy Gur-Ari
Ethan S Dyer
Behnam Neyshabur
NeurIPS Oral (2022)
Preview abstract
The ability to extrapolate from short problem instances to longer ones is an important form of out-of-distribution generalization in reasoning tasks, and is crucial when learning from datasets where longer problem instances are rare. These include theorem proving, solving quantitative mathematics problems, and reading/summarizing novels. In this paper, we run careful empirical studies exploring the length generalization capabilities of transformer-based language models. We first establish that naively finetuning transformers on length generalization tasks shows significant generalization deficiencies independent of model scale. We then show that combining pretrained large language models' in-context learning abilities with scratchpad prompting (asking the model to output solution steps before producing an answer) results in a dramatic improvement in length generalization. We run careful failure analyses on each of the learning modalities and identify common sources of mistakes that highlight opportunities in equipping language models with the ability to generalize to longer problems.
View details
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aitor Lewkowycz
Daniel Freeman
Ethan S Dyer
Guy Gur-Ari
Jaehoon Lee
Jascha Sohl-dickstein
Liam B. Fedus
TBD (2022)
Preview abstract
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to direct future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models.
To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench consists of 207 tasks, contributed by over 400 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on capabilities that are believed to be beyond current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. A team of human experts further performed all tasks, to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with human performance); model performance is remarkably similar across model classes; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit ``breakthrough'' behavior at a critical scale often involve a significant reasoning or algorithmic component; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.
View details
Preview abstract
Caliban is a command line tool that helps researchers launch and track their numerical experiments in an isolated, reproducible computing environment. It was developed by machine learning researchers and engineers, and makes it easy to go from a simple prototype running on a workstation to thousands of experimental jobs running in a Cloud environment.
View details
