{"ID":2838098,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18599","arxiv_id":"2511.18599","title":"Leveraging Language Models for Interpretable Analysis of Narratives in a Large Corpus","abstract":"Narratives drive human behavior and lay at the core of geopolitics, but have eluded quantification that would permit measurement of their overlap and evolution. We present an interpretable model that integrates an established bag-of-words (BoW) topical representation and a novel LLM-based question answering (Q\u0026A) narrative model, which share a latent Reproducing Kernel Hilbert Space representation, to quantify written documents. Our approach mitigates the cost, interpretability, and generalization challenges of using a LLM to analyze large corpora without full inference. We derive efficient functional gradient descent updates that are interpretable and structurally analogous to the self-attention mechanism in Transformers. We further introduce an in-context Q\u0026A extrapolation method inspired by Transformer architectures, enabling accurate prediction of Q\u0026A outcomes for unqueried documents.","short_abstract":"Narratives drive human behavior and lay at the core of geopolitics, but have eluded quantification that would permit measurement of their overlap and evolution. We present an interpretable model that integrates an established bag-of-words (BoW) topical representation and a novel LLM-based question answering (Q\u0026A) narra...","url_abs":"https://arxiv.org/abs/2511.18599","url_pdf":"https://arxiv.org/pdf/2511.18599v1","authors":"[\"Eric A. Bai\",\"Minling Zhou\",\"Ricardo Henao\",\"Kyle M. Schwing\",\"Lawrence Carin\"]","published":"2025-11-23T19:43:55Z","proceeding":"eess.SP","tasks":"[\"eess.SP\"]","methods":"[\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false}