# Retrieving Climate Change Disinformation by Narrative

arXiv: https://arxiv.org/abs/2603.22015 · HTML: https://mlsanity.com/paper/2603.22015/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 17 of 17)

- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models](https://mlsanity.com/paper/2501.10868/) (2025)
- [NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes](https://mlsanity.com/paper/2504.11544/) (2025)
- [Disinformation Capabilities of Large Language Models](https://mlsanity.com/paper/2311.08838/) (2023)
- [Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation](https://mlsanity.com/paper/2412.13666/) (2024)
- [Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding](https://mlsanity.com/paper/2310.18783/) (2023)
- [How Well Do Text Embedding Models Understand Syntax?](https://mlsanity.com/paper/2311.07996/) (2023)
- [Breaking Language Barriers with MMTweets: Advancing Cross-Lingual Debunked Narrative Retrieval for Fact-Checking](https://mlsanity.com/paper/2308.05680/) (2023)
- [UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections](https://mlsanity.com/paper/2505.05459/) (2025)
- [Hybrid Annotation for Propaganda Detection: Integrating LLM Pre-Annotations with Human Intelligence](https://mlsanity.com/paper/2507.18343/) (2025)
- [FaNS: a Facet-based Narrative Similarity Metric](https://mlsanity.com/paper/2309.04823/) (2023)
- [A Discourse Analysis Framework for Legislative and Social Media Debates](https://mlsanity.com/paper/2407.06149/) (2024)
- [LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval](https://mlsanity.com/paper/2505.19588/) (2025)

## Built on by (most cited first, 2 of 2)

- [Graph-Based Detection of Disinformation Narrative Diffusion between Russian and Ukrainian Telegram Channels](https://mlsanity.com/paper/2607.11894/) (2026)
- [From Repetition to Recognition: Inductive Discovery of Disinformation Narratives](https://mlsanity.com/paper/2609.11128/) (2026)

## Abstract (arXiv)

Detecting climate disinformation narratives typically relies on fixed taxonomies, which do not accommodate emerging narratives. Thus, we re-frame narrative detection as a retrieval task: given a narrative's core message as a query, rank texts from a corpus by alignment with that narrative. This formulation requires no predefined label set and can accommodate emerging narratives. We repurpose three climate disinformation datasets (CARDS, Climate Obstruction, climate change subset of PolyNarrative) for retrieval evaluation and propose SpecFi, a framework that generates hypothetical documents to bridge the gap between abstract narrative descriptions and their concrete textual instantiations. SpecFi uses community summaries from graph-based community detection as few-shot examples for generation, achieving a MAP of 0.505 on CARDS without access to narrative labels. We further introduce narrative variance, an embedding-based difficulty metric, and show via partial correlation analysis that standard retrieval degrades on high-variance narratives (BM25 loses 63.4% of MAP), while SpecFi-CS remains robust (32.7% loss). Our analysis also reveals that unsupervised community summaries converge on descriptions close to expert-crafted taxonomies, suggesting that graph-based methods can surface narrative structure from unlabeled text.