Stream of Search (SoS): Learning to Search in Language

arXiv:2404.03683v1 Announce Type: new
Abstract: Language models are rarely shown fruitful mistakes while training. They then struggle to look beyond the next token, suffering from a snowballing of errors and struggling to predict the consequence of their actions several steps ahead. In this paper, we show how language models can be taught to search by representing the process of search in language, as a flattened string -- a stream of search (SoS). We propose a unified language for search that …

abstract arxiv beyond cs.ai cs.cl cs.lg errors language language models look mistakes next paper search show struggle token training type