b'@online{Singhania_2405.02732,'b'\nTITLE = {Recall Them All: Retrieval-Augmented Language Models for Long Object List Extraction from Long Documents},\nAUTHOR = {Singhania, Sneha and Razniewski, Simon and Weikum, Gerhard},\nLANGUAGE = {eng},\nEPRINT = {2405.02732},\nEPRINTTYPE = {arXiv},\nYEAR = {2024},\nMARGINALMARK = {$\\bullet$},\nABSTRACT = {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>},\n}\n'