Language Models (LMs) often cannot be deployed because of their potential to harm users
in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using …

We describe our early efforts to red team language models in order to simultaneously
discover, measure, and attempt to reduce their potentially harmful outputs. We make three …

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented
performance in response generation, especially with visual inputs, enabling more creative …

There is growing interest in ensuring that large language models (LLMs) align with human
values. However, the alignment of such models is vulnerable to adversarial jailbreaks, which …

Deploying Large language models (LLMs) can pose hazards from harmful outputs such as
toxic or dishonest speech. Prior work has introduced tools that elicit harmful outputs in order …

A recurring challenge of crowdsourcing NLP datasets at scale is that human writers often
rely on repetitive patterns when crafting examples, leading to a lack of linguistic diversity. We …

Children can acquire language from less than 100 million words of input. Large language
models are far less data-efficient: they typically require 3 or 4 orders of magnitude more data …

The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

Large Language Models (LLMs) have demonstrated impressive zero shot performance on a
wide range of NLP tasks, demonstrating the ability to reason and apply commonsense. A …

Semantic parsing is a technique aimed at constructing a structured representation of the
meaning of a natural-language question. Recent advancements in few-shot language …