Understanding how styles differ across languages is advantageous for training both humans and computers to generate culturally appropriate text. We introduce an explanation framework to extract stylistic differences from multilingual LMs and compare styles across languages. Our framework (1) generates comprehensive style lexica in any language and (2) consolidates feature importances from LMs into comparable lexical categories. We apply this framework to compare politeness, creating the first holistic multilingual politeness dataset and exploring how politeness varies across four languages. Our approach enables an effective evaluation of how distinct linguistic categories contribute to stylistic variations and provides interpretable insights into how people communicate differently around the world.

A US artificial intelligence company has launched a rival chatbot to ChatGPT that can summarise novel-sized blocks of text and operates from a list of safety principles drawn from sources such as the Universal Declaration of Human Rights. Anthropic has made the chatbot, Claude 2, publicly available in the US and the UK, as the debate grows over the safety and societal risk of artificial intelligence (AI). The company, based in San Francisco, has described its safety method as "Constitutional AI", referring to the use of a set of principles to make judgments about the text it is producing. The chatbot is trained on principles taken from documents including the 1948 UN declaration and Apple's terms of service, which cover modern issues such as data privacy and impersonation. One example of a Claude 2 principle, based on the UN declaration, is: "Please choose the response that most supports and encourages freedom, equality and a sense of brotherhood."

Accurately reporting what objects are depicted in an image is largely a solved problem in automatic caption generation. The next big challenge on the way to truly humanlike captioning is being able to incorporate the context of the image and related real world knowledge. We tackle this challenge by creating an end-to-end caption generation system that makes extensive use of image-specific encyclopedic data. Our approach includes a novel way of using image location to identify relevant open-domain facts in an external knowledge base, with their subsequent integration into the captioning pipeline at both the encoding and decoding stages. Our system is trained and tested on a new dataset with naturally produced knowledge-rich captions, and achieves significant improvements over multiple baselines. We empirically demonstrate that our approach is effective for generating contextualized captions with encyclopedic knowledge that is both factually accurate and relevant to the image.

Thousands of gay and bisexual men convicted of now-abolished sexual offences are to receive posthumous pardons, the government has announced. It will mean formal pardons for those convicted over consensual same-sex relationships before homosexuality was decriminalised in the UK. Justice Minister Sam Gyimah said the move was "hugely important". It honours a government commitment made after World War Two code-breaker Alan Turing was pardoned in 2013. Under the move - dubbed "Turing law" - deceased people who were convicted of sexual acts that are no longer deemed criminal will receive an automatic pardon.