The US military action in Venezuela breaches international law and the UK should make clear it is unacceptable, the chair of the Commons Foreign Affairs Committee has said. Dame Emily Thornberry is the most senior Labour MP so far to criticise Donald Trump's strikes on the country over the weekend, which saw President Nicolas Maduro and his wife captured. The UK government has so far refused to say whether the move was illegal, insisting it is for the Americans to lay out the legal basis for the action. But the US president's actions have been criticised by some Labour MPs, as well as the leaders of the Lib Dems, Greens and the SNP. Dame Emily told BBC Radio 4's Westminster Hour the strikes were not a legal action and she cannot think of anything that could be a proper justification.

In this paper, we present our finding that prepending a Task-Agnostic Prefix Prompt (TAPP) to the input improves the instruction-following ability of various Large Language Models (LLMs) during inference. TAPP is different from canonical prompts for LLMs in that it is a fixed prompt prepended to the beginning of every input regardless of the target task for zero-shot generalization. We observe that both base LLMs (i.e. not fine-tuned to follow instructions) and instruction-tuned models benefit from TAPP, resulting in 34.58% and 12.26% improvement on average, respectively. This implies that the instruction-following ability of LLMs can be improved during inference time with a fixed prompt constructed with simple heuristics. We hypothesize that TAPP assists language models to better estimate the output distribution by focusing more on the instruction of the target task during inference. In other words, such ability does not seem to be sufficiently activated in not only base LLMs but also many instruction-fine-tuned LLMs. All experiments are reproducible from https://github.com/seonghyeonye/TAPP.