analiza aiqbench
This research presents an end-to-end framework that uses iterative LLM inference to automatically construct interpretopic taxonomies from unlabeled text, eliminating the need for predefined labels or seed topics. Evaluated on 2024 U.S. presidential election ads, the method enables scalable analysis of issue prevalence and moral framing in large-scale social media corpora. The approach advances the field of unsupervised topic modeling by offering a robust pipeline for organizing evolving political discourse without human intervention.
Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising
arXiv:2510.15125v3 Announce Type: replace-cross Abstract: Social media platforms play a pivotal role in shaping political discourse, but the scale and rapid evolution of online content make systematic analysis difficult. We introduce an end-to-end framework for inducing an interpretable topic taxonomy from unlabeled text corpora. The framework combines embedding-based clustering with iterative large language model (LLM) inference to construct a topic taxonomy without requiring predefined labels or seed topics. It first synthesizes candidate topics from document clusters and then uses the resulting taxonomy to assign consistent topic labels across clusters. We evaluate the approach through a case study of political advertising ahead of the 2024 U.S. presidential election. We use the induced taxonomy to support downstream analyses of issue prevalence, moral framing, advertising spend, and demographic exposure patterns. These results suggest that iterative taxonomy construction can provide a scalable and interpretable approach to organizing large unlabeled text corpora while supporting substantive downstream analysis.
Abstract:Social media platforms play a pivotal role in shaping political discourse, but the scale and rapid evolution of online content make systematic analysis difficult. We introduce an end-to-end framework for inducing an interpretable topic taxonomy from unlabeled text corpora. The framework combines embedding-based clustering with iterative large language model (LLM) inference to construct a topic taxonomy without requiring predefined labels or seed topics. It first synthesizes candidate topics from document clusters and then uses the resulting taxonomy to assign consistent topic labels across clusters. We evaluate the approach through a case study of political advertising ahead of the 2024 U.S. presidential election. We use the induced taxonomy to support downstream analyses of issue prevalence, moral framing, advertising spend, and demographic exposure patterns. These results suggest that iterative taxonomy construction can provide a scalable and interpretable approach to organizing large unlabeled text corpora while supporting substantive downstream analysis.
Accepted to AACL-IJCNLP 2026 Findings. Camera-ready
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG); Social and Information Networks (cs.SI)
arXiv:2510.15125 [cs.CL]
(or arXiv:2510.15125v3 [cs.CL] for this version)
Text integral sub licența deschisă a publicației · 180 cuvinte
Subiecte conexe
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
Presentation: Building Evals for AI Adoption: from Principles to Practice
InfoQ · 29 mai 2026
Research Note: Filtering Subversion-Relevant Information From Pretraining Data Is Feasible
LessWrong · 5 oct. 2026
Thousand-dimensional structure
AI Alignment Forum · 30 iul. 2026