Can Large Language Models Recall Reference Location Like Humans?

arXiv:2402.17010v1 Announce Type: new
Abstract: When completing knowledge-intensive tasks, humans sometimes need not just an answer but also a corresponding reference passage for auxiliary reading. Previous methods required obtaining pre-segmented article chunks through additional retrieval models. This paper explores leveraging the parameterized knowledge stored during the pre-training phase of large language models (LLMs) to independently recall reference passage from any starting position. We propose a two-stage framework that simulates the scenario of humans recalling easily forgotten references. Initially, the LLM …

abstract article arxiv cs.ai cs.cl humans knowledge language language models large language large language models location paper pre-training reading recall reference retrieval tasks through training type