Rank-Turbulence Delta and Interpretable Approaches to Stylometric Delta Metrics

arXiv:2604.19499v1 Announce Type: new Abstract: This article introduces two new measures for authorship attribution - Rank-Turbulence Delta and Jensen-Shannon Delta - which generalise Burrows's classical Delta by applying distance functions designed for probabilistic distributions. We first set out the theoretical basis of the measures, contrasting centred and uncentred z-scoring of word-frequency vectors and re-casting the uncentred vectors as probability distributions. Building on this representation, we develop a token-level decomposition that renders every Delta distance numerically interpretable, thereby facilitating close reading and the validation of results. The effectiveness of the methods is assessed on four literary corpora in English, German, French and Russian. The English, German and French datasets are compiled from Project Gutenberg, whereas the Russian benchmark is the SOCIOLIT corpus containing 755 works by 180 authors spanning the eighteenth to the twenty-first centuries. Rank-Turbulence Delta attains attribution accuracy comparable with Cosine Delta; Jensen-Shannon Delta consistently matches or exceeds the performance of canonical Burrows's Delta. Finally, several established attribution algorithms are re-evaluated on the extended SOCIOLIT corpus.

Related

• On the Importance and Evaluation of Narrativity in Natural Language AI Explanations
• From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
• Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution
• When Self-Reference Fails to Close: Matrix-Level Dynamics in Large Language Models

Source: arXiv cs.CL | 2026-04-22