FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval

Autor:	Wang, Jinlin, Wang, Suyuchen, Xia, Ziwen, Hong, Sirui, Zhu, Yun, Liu, Bang, Wu, Chenglin
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, yet they struggle with tasks requiring the simultaneous retrieval of multiple facts, especially during generation. This paper identifies a novel "lost-in-the-middle" phenomenon, where LLMs progressively lose track of critical information throughout the generation process, resulting in incomplete or inaccurate retrieval. To address this challenge, we introduce Find All Crucial Texts (FACT), an iterative retrieval method that refines context through successive rounds of rewriting. This approach enables models to capture essential facts incrementally, which are often overlooked in single-pass retrieval. Experiments demonstrate that FACT substantially enhances multi-fact retrieval performance across various tasks, though improvements are less notable in general-purpose QA scenarios. Our findings shed light on the limitations of LLMs in multi-fact retrieval and underscore the need for more resilient long-context retrieval strategies. Comment: Work in Progress
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.21012 Zobrazit plný text záznamu View this record from Arxiv