LLM-Augmented Changepoint Detection: A Framework for Ensemble Detection and Automated Explanation

2026-01-06

arXiv.org

AI Summary

This work proposes an ensemble framework integrating ten statistical change-point detection algorithms to address the challenges of method selection difficulty, performance instability, and lack of contextual interpretability in traditional approaches. For the first time, large language models (LLMs) combined with retrieval-augmented generation (RAG) are incorporated into change-point analysis, enabling highly robust detection alongside the automatic generation of interpretable narratives that link detected change points to relevant historical events. The framework supports domain-specific interpretability by leveraging user-provided private documents and demonstrates superior performance over individual algorithms across multiple domains, including finance, political science, and environmental science. Moreover, it effectively translates statistical findings into actionable decision-making insights.

Technology Category

• Machine Learning: Ensemble Methods
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This paper introduces a novel changepoint detection framework that combines ensemble statistical methods with Large Language Models (LLMs) to enhance both detection accuracy and the interpretability of regime changes in time series data. Two critical limitations in the field are addressed. First, individual detection methods exhibit complementary strengths and weaknesses depending on data characteristics, making method selection non-trivial and prone to suboptimal results. Second, automated, contextual explanations for detected changes are largely absent. The proposed ensemble method aggregates results from ten distinct changepoint detection algorithms, achieving superior performance and robustness compared to individual methods. Additionally, an LLM-powered explanation pipeline automatically generates contextual narratives, linking detected changepoints to potential real-world historical events. For private or domain-specific data, a Retrieval-Augmented Generation (RAG) solution enables explanations grounded in user-provided documents. The open source Python framework demonstrates practical utility in diverse domains, including finance, political science, and environmental science, transforming raw statistical output into actionable insights for analysts and decision-makers.

Problem

• changepoint detection
• ensemble methods
• interpretability
• Large Language Models
• time series

Innovation

• changepoint detection
• Large Language Models
• ensemble methods
• Retrieval-Augmented Generation
• time series interpretability