@online{Singhania_2405.02732,
TITLE = {Recall Them All: Retrieval-Augmented Language Models for Long Object List Extraction from Long Documents},
AUTHOR = {Singhania, Sneha and Razniewski, Simon and Weikum, Gerhard},
LANGUAGE = {eng},
EPRINT = {2405.02732},
EPRINTTYPE = {arXiv},
YEAR = {2024},
MARGINALMARK = {$\bullet$},
ABSTRACT = {Methods for relation extraction from text mostly focus on high precision, at<br>the cost of limited recall. High recall is crucial, though, to populate long<br>lists of object entities that stand in a specific relation with a given<br>subject. Cues for relevant objects can be spread across many passages in long<br>texts. This poses the challenge of extracting long lists from long texts. We<br>present the L3X method which tackles the problem in two stages: (1)<br>recall-oriented generation using a large language model (LLM) with judicious<br>techniques for retrieval augmentation, and (2) precision-oriented<br>scrutinization to validate or prune candidates. Our L3X method outperforms<br>LLM-only generations by a substantial margin.<br>},
}