# Leveraging Language Models for Interpretable Analysis of Narratives in a Large Corpus

Source: [Leveraging Language Models for Interpretable Analysis of Narratives in a Large Corpus](<https://www.sota2.com/research/paper/6925381dd6b0dd334292f4ca>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-26T05:04:09.144Z

Authors: Eric A. Bai, Minling Zhou, Ricardo Henao, Kyle M. Schwing, Lawrence Carin

Published: 2025-11-23T19:43:55.000Z

## 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&A) 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&A extrapolation method inspired by Transformer architectures, enabling accurate prediction of Q&A outcomes for unqueried documents.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.18599>)

[PDF](<https://arxiv.org/pdf/2511.18599.pdf>)
