A new 292-example benchmark shows the best closed-source LLM retrieves literary quotations from full novels better than one human expert, while open-weight models lag sharply.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Literary Evidence Retrieval via Long-Context Language Models
A new 292-example benchmark shows the best closed-source LLM retrieves literary quotations from full novels better than one human expert, while open-weight models lag sharply.