Automated Detection and Structuring of Social Tipping Point Evidence in Climate related Documents: A Modular AI Framework

arXiv cs.CL Papers

Summary

This paper introduces an open modular transformer-based framework for detecting and structuring social tipping point evidence in climate documents, utilizing models like DistilBERT, RoBERTa, Mistral 7B, and LLaMA 3.2 3B, with evaluation on expert-labeled benchmarks.

arXiv:2609.12254v1 Announce Type: new Abstract: The climate literature has grown faster than review teams can read it. That gap matters most for a concept like the environmental social tipping point, the threshold at which a small change triggers rapid, self-reinforcing change in a social system. Evidence of this kind of shift is usually contained in one or two paragraphs within a longer document. As a result, existing text mining tools-which categorize entire documents by topic or highlight isolated claims-leave an expanding set of important evidence without any systematic method for discovery or organization. This paper presents an open and modular transformer-based framework that detects and structures social tipping point evidence at the passage level. The framework joins five components into a single deployable workflow: a DistilBERT boundary splitter for segmentation, an iteratively augmented RoBERTa classifier for detection, a Mistral 7B model that rewrites each detected passage for clarity, a LLaMA 3.2 3B model that rates the passage against five published social tipping point criteria, and a Milvus vector store for semantic retrieval. The system is wrapped in a Streamlit interface backed by MinIO object storage. Evaluated on a 163-passage benchmark labelled by GPT-4.1 and a 51-passage set reviewed by experts, the splitter surpassed three competing methods on a nine-metric composite score (6.137). The tuned RoBERTa model achieved 71.4 percent accuracy with a Cohen's kappa of 0.337 on the full benchmark, and 87.5 percent accuracy with a kappa of 0.742 on passages with labels, outperforming both a climate-focused model and untuned language models.
Original Article
View Cached Full Text

Cached at: 09/14/26, 08:30 AM

# Automated Detection and Structuring of Social Tipping Point Evidence in Climate related Documents: A Modular AI Framework
Source: [https://arxiv.org/abs/2609.12254](https://arxiv.org/abs/2609.12254)
Authors:[Kavindu Perera](https://arxiv.org/search/cs?searchtype=author&query=Perera,+K),[Mohammad Abaeiani](https://arxiv.org/search/cs?searchtype=author&query=Abaeiani,+M),[Ekaterina Gilman](https://arxiv.org/search/cs?searchtype=author&query=Gilman,+E),[Lauri Loven](https://arxiv.org/search/cs?searchtype=author&query=Loven,+L),[Mourad Oussalah](https://arxiv.org/search/cs?searchtype=author&query=Oussalah,+M),[Tassos Kanellos](https://arxiv.org/search/cs?searchtype=author&query=Kanellos,+T),[Beatrice Gobbo](https://arxiv.org/search/cs?searchtype=author&query=Gobbo,+B),[Dante Adami](https://arxiv.org/search/cs?searchtype=author&query=Adami,+D),[Nicolò Ferriani](https://arxiv.org/search/cs?searchtype=author&query=Ferriani,+N),[Maximiliano Romero](https://arxiv.org/search/cs?searchtype=author&query=Romero,+M),[Pierre Rossel](https://arxiv.org/search/cs?searchtype=author&query=Rossel,+P),[Marc Bonazountas](https://arxiv.org/search/cs?searchtype=author&query=Bonazountas,+M),[Christina Deligianni](https://arxiv.org/search/cs?searchtype=author&query=Deligianni,+C),[Nikos Xyderis](https://arxiv.org/search/cs?searchtype=author&query=Xyderis,+N),[Artur Bogucki](https://arxiv.org/search/cs?searchtype=author&query=Bogucki,+A),[Lampros Argyriou](https://arxiv.org/search/cs?searchtype=author&query=Argyriou,+L),[Prasasthy Balasubramanian](https://arxiv.org/search/cs?searchtype=author&query=Balasubramanian,+P)

[View PDF](https://arxiv.org/pdf/2609.12254)

> Abstract:The climate literature has grown faster than review teams can read it\. That gap matters most for a concept like the environmental social tipping point, the threshold at which a small change triggers rapid, self\-reinforcing change in a social system\. Evidence of this kind of shift is usually contained in one or two paragraphs within a longer document\. As a result, existing text mining tools\-which categorize entire documents by topic or highlight isolated claims\-leave an expanding set of important evidence without any systematic method for discovery or organization\. This paper presents an open and modular transformer\-based framework that detects and structures social tipping point evidence at the passage level\. The framework joins five components into a single deployable workflow: a DistilBERT boundary splitter for segmentation, an iteratively augmented RoBERTa classifier for detection, a Mistral 7B model that rewrites each detected passage for clarity, a LLaMA 3\.2 3B model that rates the passage against five published social tipping point criteria, and a Milvus vector store for semantic retrieval\. The system is wrapped in a Streamlit interface backed by MinIO object storage\. Evaluated on a 163\-passage benchmark labelled by GPT\-4\.1 and a 51\-passage set reviewed by experts, the splitter surpassed three competing methods on a nine\-metric composite score \(6\.137\)\. The tuned RoBERTa model achieved 71\.4 percent accuracy with a Cohen's kappa of 0\.337 on the full benchmark, and 87\.5 percent accuracy with a kappa of 0\.742 on passages with labels, outperforming both a climate\-focused model and untuned language models\.

## Submission history

From: Prasasthy Balasubramanian \[[view email](https://arxiv.org/show-email/9f38865d/2609.12254)\] **\[v1\]**Thu, 10 Sep 2026 22:21:16 UTC \(1,379 KB\)

Similar Articles

LLM-based Detection of Manipulative Political Narratives

Hugging Face Daily Papers

A computational framework combining prompt-based filtering and unsupervised clustering to identify manipulative political narrative clusters from social media posts without predefined categories.