Understand the Implication: Learning to Think for Pragmatic Understanding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915346772918272 |
|---|---|
| author | Sravanthi, Settaluri Lakshmi Maharaj, Kishan Gunnu, Sravani Mishra, Abhijit Bhattacharyya, Pushpak |
| author_facet | Sravanthi, Settaluri Lakshmi Maharaj, Kishan Gunnu, Sravani Mishra, Abhijit Bhattacharyya, Pushpak |
| contents | Pragmatics, the ability to infer meaning beyond literal interpretation, is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance remains underexplored. Existing methods rely on annotated labels but overlook the reasoning process humans naturally use to interpret implicit meaning. To bridge this gap, we introduce a novel pragmatic dataset, ImpliedMeaningPreference, that includes explicit reasoning (thoughts) for both correct and incorrect interpretations. Through preference-tuning and supervised fine-tuning, we demonstrate that thought-based learning significantly enhances LLMs' pragmatic understanding, improving accuracy by 11.12% across model families. We further discuss a transfer-learning study where we evaluate the performance of thought-based training for the other tasks of pragmatics (presupposition, deixis) that are not seen during the training time and observe an improvement of 16.10% compared to label-trained models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13559 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Understand the Implication: Learning to Think for Pragmatic Understanding Sravanthi, Settaluri Lakshmi Maharaj, Kishan Gunnu, Sravani Mishra, Abhijit Bhattacharyya, Pushpak Computation and Language Artificial Intelligence Pragmatics, the ability to infer meaning beyond literal interpretation, is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance remains underexplored. Existing methods rely on annotated labels but overlook the reasoning process humans naturally use to interpret implicit meaning. To bridge this gap, we introduce a novel pragmatic dataset, ImpliedMeaningPreference, that includes explicit reasoning (thoughts) for both correct and incorrect interpretations. Through preference-tuning and supervised fine-tuning, we demonstrate that thought-based learning significantly enhances LLMs' pragmatic understanding, improving accuracy by 11.12% across model families. We further discuss a transfer-learning study where we evaluate the performance of thought-based training for the other tasks of pragmatics (presupposition, deixis) that are not seen during the training time and observe an improvement of 16.10% compared to label-trained models. |
| title | Understand the Implication: Learning to Think for Pragmatic Understanding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.13559 |