Search papers, labs, and topics across Lattice.
This study redefines intertextuality extraction as an agentic task for large language models (LLMs), enabling them to identify and label text reuse with precision across classical Chinese histories. By employing a five-dimensional typology and validating the approach against expert adjudication of 2,533 intertextual pairs, the authors reveal significant variability in LLM performance, with precision ranging from 56% to 93%. The findings indicate that while surface-level dimensions of reuse are consistently annotated, deeper inferential dimensions remain contentious, highlighting the complexities of intertextual interpretation over time.
LLMs can achieve up to 93% precision in identifying intertextuality, but their reliability varies dramatically based on the complexity of the reuse dimensions involved.
Computational approaches to intertextuality have advanced from string matching to neural retrieval, yet their outputs, similarity scores and parallel-passage lists, identify where texts reuse one another without characterizing how or why. We recast fine-grained intertextuality extraction as an agentic task in which a large language model (LLM) reads two text units in full and, through a constrained tool interface, must ground each proposed reuse in exact character spans on both sides and label it under a five-dimension typology of reuse (form, aspect, source-marking, function, stance). We validate the approach on an exhaustive comparison of the Analects with the Book of Han, where three domain experts adjudicate a pooled multi-model candidate set into a benchmark of 2,533 intertextual pairs. Against this standard we study twelve LLMs, reporting precision (56%-93%), a 51$\times$ cost spread at comparable quality, and how well their confidence is calibrated. Expert agreement traces a reliability gradient: dimensions legible on the textual surface are annotated consistently, while those requiring inference of intent are contested, delimiting the claims such annotation supports. Scaling the validated extractor to the full Twenty-Four Histories (65,380 comparisons, 5,766 pairs) recovers corpus-level structure a similarity score cannot express. The interpretive composition of citation shows no systematic change across eighteen centuries, yet the same passage is quoted less and less literally. Stability in the aggregate with drift in the individual case is what a cultural-attraction account expects. We release the extraction protocol and the expert-adjudicated benchmark.
