“you can automatically learn soft prompts with backprop so.. the job "prompt engineering" isn't going to stick around for too long given it's automatable. https://arxiv.org/abs/2302.06541 That is not to say, that integrating LLMs won't create a lot of jobs. Think of it as systems engineering. Knowing how computers work, as well as a software engineer doe…”
Towards Agile Text Classifiers for Everyone
Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digital assistants and chatbots. However, different policies require different classifiers, and safety policies themselves improve from iteration and adaptation. This paper introduces and evaluates methods for agile text classification, whereby classifiers are trained using small, targeted datasets that can be quickly developed for a particular policy. Experimenting with 7 datasets from three safety-related domains, comprising 15 annotation schemes, led to our key finding: prompt-tuning large language models, like PaLM 62B, with a labeled dataset of as few as 80 examples can achieve state-of-the-art performance. We argue that this enables a paradigm shift for text classification, especially for models supporting safer online discourse. Instead of collecting millions of examples to attempt to create universal safety classifiers over months or years, classifiers could be tuned using small datasets, created by individuals or small organizations, tailored for specific use cases, and iterated on and adapted in the time-span of a day.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“More like: the accessibility is what will make it go around. The accessibility is what changes everything! Getting an easy to use interface (instructions) over python changes the accessibility from the denizens of this website to ~anyone with a computer If you're interested, see this paper that argues that point: https://arxiv.org/abs/2302.06541 Essenti…”
“Re: https://arxiv.org/abs/2302.06541 - how are we supposed to take the phrase "agile text classification" seriously? They could have just said "efficient". But no - they had to go for "agile".”