Mihir arora biography template

Abstract

Massive high-quality data, both pre-training raw texts and post-training annotations, have been carefully prepared to incubate advanced large language models (LLMs). In contrast, for information extraction (IE), pre-training information, such as BIO-tagged sequences, are hard to scale up. We show that IE models can act as free riders on LLM resources by reframing next-token prediction into extraction for tokens already present in the context. Specifically, our proposed next tokens extraction (NTE) paradigm learns a versatile IE model, \our, with M extractive data converted from LLM’s pre-training and post-training information. Under the few-shot setting, \ouradapts effectively to traditional and complex instruction-following IE with better performance than existing pre-trained IE model

•