Towards Intention-aligned Reviews Summarization: Enhancing LLM Outputs with Pragmatic Cues

Maria Miro Maestre, Robiert Sepulveda-Torres, Ernesto Luis Estevanell-Valladares, Armando Suarez Cueto, Elena Lloret


Abstract
Recent advancements in Natural Language Processing (NLP) have allowed systems to address complex tasks involving cultural knowledge, multi-step reasoning, and inference. While significant progress has been made in text summarization guided by specific instructions or stylistic cues, the integration of pragmatic aspects like communicative intentions remains underexplored, particularly in non-English languages. This study emphasizes communicative intentions as central to summary generation, classifying Spanish product reviews by intent and using prompt engineering to produce intention-aligned summaries. Results indicate challenges for large language models (LLMs) in processing extensive document clusters, with summarization accuracy heavily dependent on prior model exposure to similar intentions. Common intentions such as complimenting and criticizing are reliably handled, whereas less frequent ones like promising or questioning pose greater difficulties. These findings suggest that integrating communicative intentions into summarization tasks can significantly enhance summary relevance and clarity, thereby improving user experience in product review analysis.
Anthology ID:
2025.ranlp-1.85
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
737–747
Language:
URL:
https://aclanthology.org/2025.ranlp-1.85/
DOI:
Bibkey:
Cite (ACL):
Maria Miro Maestre, Robiert Sepulveda-Torres, Ernesto Luis Estevanell-Valladares, Armando Suarez Cueto, and Elena Lloret. 2025. Towards Intention-aligned Reviews Summarization: Enhancing LLM Outputs with Pragmatic Cues. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 737–747, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Towards Intention-aligned Reviews Summarization: Enhancing LLM Outputs with Pragmatic Cues (Miro Maestre et al., RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.85.pdf