Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News

• URL: http://arxiv.org/abs/2606.26489v1
• Date: Thu, 25 Jun 2026 00:48:40 GMT
• Title: Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News
• Abstract summary: We present two approaches for classifying sentences from German-language climate news articles as threat-oriented, solution-oriented, both, or neither.<n>The first approach uses few-shot prompting with an open-weights large language model (Llama 4 Maverick), employing chain-of-thought reasoning and structured output with confidence scoring.<n>The second approach fine-tunes a German BERT model (deepset/gbert-large) for sentence-pair classification, where the preceding sentence provides contextual information for the target sentence.
• Score: 1.4465033892011254
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: News media play a central role in shaping public perceptions of climate change, and whether coverage emphasizes threats or solutions has measurable effects on audience engagement and policy support. Automated detection of these framing patterns at the sentence level would allow researchers to analyze large corpora that are infeasible to code manually. We present a systematic comparison of two approaches for classifying sentences from German-language climate news articles as threat-oriented, solution-oriented, both, or neither. The first approach uses few-shot prompting with an open-weights large language model (Llama 4 Maverick), employing chain-of-thought reasoning and structured output with confidence scoring. The second approach fine-tunes a German BERT model (deepset/gbert-large) for sentence-pair classification, where the preceding sentence provides contextual information for the target sentence. Both approaches implement two independent binary classifiers, one for threat framing and one for solution framing. We evaluate both methods on a corpus of 440 Austrian newspaper articles that were manually coded following a detailed coding scheme developed with domain experts. The fine-tuned BERT classifiers achieve an F1 score of 0.83 for both the threat and solution tasks, while the LLM-based classifiers reach an F1 of 0.78. An ablation study confirms that providing the preceding sentence as context improves BERT classification performance substantially compared to single-sentence input. These results contribute to the growing body of work comparing fine-tuned encoder models with prompted generative models for text classification in computational social science.

Related papers

• Bangla Sentence Function Classification: Corpus Development, Model Benchmarking, and Interpretability [0.15635627702544694]
  This paper introduces a corpus of 10,000 Bangla sentences, manually annotated into four functional categories.<n>We evaluate multiple feature representations, including Bag-of-Words (BoW), TF-IDF, and Word2Vec.<n> Experimental results show that TF-IDF consistently outperforms Word2Vec.
  arXiv  Detail & Related papers  (2026-09-12T10:45:24Z)
• SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space [11.534994345027362]
  Multimodal large language models (MLLMs) have shown impressive capabilities in vision-language tasks such as reasoning segmentation.<n>We introduce a novel adversarial paraphrasing task: generating grammatically correct paraphrases that preserve the original query meaning while degrading segmentation performance.<n>We introduce SPARTA-a black-box, sentence-level optimization method that operates in the low-dimensional semantic latent space of a text autoencoder.
  arXiv  Detail & Related papers  (2025-10-28T14:09:05Z)
• Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning [13.725832389453911]
  Citation classification is pivotal for scholarly analysis.<n>Previous works suggest fine-tuning pretrained language models (PLMs) on citation classification.<n>We present a novel framework, Citss, that adapts the PLMs to overcome these challenges.
  arXiv  Detail & Related papers  (2025-05-20T15:05:27Z)
• Localizing Factual Inconsistencies in Attributable Text Generation [74.11403803488643]
  We introduce QASemConsistency, a new formalism for localizing factual inconsistencies in attributable text generation.<n>We show that QASemConsistency yields factual consistency scores that correlate well with human judgments.
  arXiv  Detail & Related papers  (2024-10-09T22:53:48Z)
• Co-training for Low Resource Scientific Natural Language Inference [65.37685198688538]
  We propose a novel co-training method that assigns weights based on the training dynamics of the classifiers to the distantly supervised labels. By assigning importance weights instead of filtering out examples based on an arbitrary threshold on the predicted confidence, we maximize the usage of automatically labeled data. The proposed method obtains an improvement of 1.5% in Macro F1 over the distant supervision baseline, and substantial improvements over several other strong SSL baselines.
  arXiv  Detail & Related papers  (2024-06-20T18:35:47Z)
• Verifying the Robustness of Automatic Credibility Assessment [50.55687778699995]
  We show that meaning-preserving changes in input text can mislead the models. We also introduce BODEGA: a benchmark for testing both victim models and attack methods on misinformation detection tasks. Our experimental results show that modern large language models are often more vulnerable to attacks than previous, smaller solutions.
  arXiv  Detail & Related papers  (2023-03-14T16:11:47Z)
• Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification [66.02091763340094]
  Like a Good Nearest Neighbor (LaGoNN) is a modification to SetFit that introduces no learnable parameters but alters input text with information from its nearest neighbor. LaGoNN is effective at flagging undesirable content and text classification, and improves the performance of SetFit.
  arXiv  Detail & Related papers  (2023-02-17T15:43:29Z)
• Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework [68.04940365847543]
  We propose a semi-supervised sentence embedding framework, GenSE, that effectively leverages large-scale unlabeled data. Our method include three parts: 1) Generate: A generator/discriminator model is jointly trained to synthesize sentence pairs from open-domain unlabeled corpus; 2) Discriminate: Noisy sentence pairs are filtered out by the discriminator to acquire high-quality positive and negative sentence pairs; 3) Contrast: A prompt-based contrastive approach is presented for sentence representation learning with both annotated and synthesized data.
  arXiv  Detail & Related papers  (2022-10-30T10:15:21Z)
• InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings [61.77760317554826]
  This paper proposes an information-d contrastive learning framework for learning unsupervised sentence embeddings, termed InfoCSE. We evaluate the proposed InfoCSE on several benchmark datasets w.r.t the semantic text similarity (STS) task. Experimental results show that InfoCSE outperforms SimCSE by an average Spearman correlation of 2.60% on BERT-base, and 1.77% on BERT-large.
  arXiv  Detail & Related papers  (2022-10-08T15:53:19Z)
• Speaker Embedding-aware Neural Diarization: a Novel Framework for Overlapped Speech Diarization in the Meeting Scenario [51.5031673695118]
  We reformulate overlapped speech diarization as a single-label prediction problem. We propose the speaker embedding-aware neural diarization (SEND) system.
  arXiv  Detail & Related papers  (2022-03-18T06:40:39Z)
• Co-training an Unsupervised Constituency Parser with Weak Supervision [33.63314110665062]
  We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. We show that the interplay between them helps improve the accuracy of both, and as a result, effectively parse.
  arXiv  Detail & Related papers  (2021-10-05T18:45:06Z)
• Exploiting Global Contextual Information for Document-level Named Entity Recognition [46.99922251839363]
  We propose a model called Global Context enhanced Document-level NER (GCDoc) At word-level, a document graph is constructed to model a wider range of dependencies between words. At sentence-level, for appropriately modeling wider context beyond single sentence, we employ a cross-sentence module. Our model reaches F1 score of 92.22 (93.40 with BERT) on CoNLL 2003 dataset and 88.32 (90.49 with BERT) on Ontonotes 5.0 dataset.
  arXiv  Detail & Related papers  (2021-06-02T01:52:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.