'The Order in the Horse's Heart': A Case Study in LLM-Assisted Stylometry for the Discovery of Biblical Allusion in Modern Literary Fiction

TL;DR

This paper introduces a dual-track LLM-based pipeline for detecting biblical allusions in literary fiction, validated on Cormac McCarthy's novels, combining embedding, register analysis, and cross-validation techniques.

Contribution

It presents a novel, multi-faceted approach integrating LLMs and stylometry to identify biblical allusions, achieving significant recall and validation against scholarly references.

Findings

Recovered 62 of 115 known allusions (54% recall)

Recall varies from 30% to 80% depending on connection type

Pipeline surfaces 349 allusions in McCarthy's novels

Abstract

We present a dual-track pipeline for detecting biblical allusions in literary fiction and apply it to the novels of Cormac McCarthy. A bottom-up embedding track uses inverse document frequency to identify rare vocabulary shared with the King James Bible, embeds occurrences in their local context for sense disambiguation, and passes candidate passage pairs through cascaded LLM review. A top-down register track asks an LLM to read McCarthy's prose undirected to any specific biblical passage for comparison, catching allusions not distinguished by word or phrase rarity. Both tracks are cross-validated by a long-context model that holds entire novels alongside the KJV in a single pass, and every finding is checked against published scholarship. Restricting attention to allusions that carry a textual echo--shared phrasing, reworked vocabulary, or transplanted cadence--and distinguishing literary allusions proper from signposted biblical references (similes naming biblical figures, characters overtly citing scripture), the pipeline surfaces 349 allusions across the corpus. Among a target set of 115 previously documented allusions retrieved through human review of the academic literature, the pipeline independently recovers 62 (54% recall), with recall varying by connection type from 30% (transformed imagery) to 80% (register collisions). We contextualise these results with respect to the value-add from LLMs as assistants to mechanical stylometric analyses, and their potential to facilitate the statistical study of intertextuality in massive literary corpora.