Miles Redcliffe, and Matthew Blackwood. “Improving Interpretability in Large Language Models through Layer Wise Relevance Propagation for Identifying Latent Reasoning Biases”. International Journal of Artificial Intelligence Research 1, no. 2 (May 12, 2026). Accessed May 14, 2026. https://isipress.org/index.php/IJAIR/article/view/142.