Summary
Researchers Kirill Solovev and Jana Lasser present a multilingual joint entity-relation extraction pipeline that uses open-source large language models (LLMs) to automatically build political-elite networks from multilingual news text. Addressing a central question in comparative politics—whether political elites organize into rent-seeking coalitions that capture public resources or civic networks that sustain governance—the method replaces traditional intensive manual coding and simple co-occurrence-based text-as-data approaches. By relying on open-source models rather than proprietary APIs, the pipeline offers a reproducible, cost-effective path to observing complex, informal, and adversarial elite ties at scale. The paper is available on arXiv (2606.27347) and was shared on zhichai.net on 2026-06-27.
Paper Overview
Field: NLP
Authors: Kirill Solovev, Jana Lasser
Published: 2026-06-27
arXiv:
2606.27347Abstract
Whether political elites organise into rent-seeking coalitions that capture public resources or civic networks that sustain governance is a central question in comparative politics. Yet observing these complex, informal, and adversarial ties at scale has historically required intensive manual coding, while automated text-as-data methods have largely been limited to simple co-occurrence. Recent large language model (LLM) approaches offer a path forward but often rely on proprietary APIs and lack cross-lingual robustness.
This work proposes a multilingual joint entity-relation extraction pipeline that leverages open-source LLMs to automatically extract political-elite networks from multilingual news text, without the need for proprietary APIs.
---
*Auto-collected on 2026-06-27*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178208203