Improving Narrative Classification and Explanation via Fine Tuned Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915478863085568 |
|---|---|
| author | Tyagi, Rishit Bouri, Rahul Gupta, Mohit |
| author_facet | Tyagi, Rishit Bouri, Rahul Gupta, Mohit |
| contents | Understanding covert narratives and implicit messaging is essential for analyzing bias and sentiment. Traditional NLP methods struggle with detecting subtle phrasing and hidden agendas. This study tackles two key challenges: (1) multi-label classification of narratives and sub-narratives in news articles, and (2) generating concise, evidence-based explanations for dominant narratives. We fine-tune a BERT model with a recall-oriented approach for comprehensive narrative detection, refining predictions using a GPT-4o pipeline for consistency. For narrative explanation, we propose a ReACT (Reasoning + Acting) framework with semantic retrieval-based few-shot prompting, ensuring grounded and relevant justifications. To enhance factual accuracy and reduce hallucinations, we incorporate a structured taxonomy table as an auxiliary knowledge base. Our results show that integrating auxiliary knowledge in prompts improves classification accuracy and justification reliability, with applications in media analysis, education, and intelligence gathering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04077 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Narrative Classification and Explanation via Fine Tuned Language Models Tyagi, Rishit Bouri, Rahul Gupta, Mohit Computation and Language Understanding covert narratives and implicit messaging is essential for analyzing bias and sentiment. Traditional NLP methods struggle with detecting subtle phrasing and hidden agendas. This study tackles two key challenges: (1) multi-label classification of narratives and sub-narratives in news articles, and (2) generating concise, evidence-based explanations for dominant narratives. We fine-tune a BERT model with a recall-oriented approach for comprehensive narrative detection, refining predictions using a GPT-4o pipeline for consistency. For narrative explanation, we propose a ReACT (Reasoning + Acting) framework with semantic retrieval-based few-shot prompting, ensuring grounded and relevant justifications. To enhance factual accuracy and reduce hallucinations, we incorporate a structured taxonomy table as an auxiliary knowledge base. Our results show that integrating auxiliary knowledge in prompts improves classification accuracy and justification reliability, with applications in media analysis, education, and intelligence gathering. |
| title | Improving Narrative Classification and Explanation via Fine Tuned Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.04077 |