Entailed Between the Lines: Incorporating Implication into NLI
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929679424815104 |
|---|---|
| author | Havaldar, Shreya Alvari, Hamidreza Palowitch, John Hosseini, Mohammad Javad Buthpitiya, Senaka Fabrikant, Alex |
| author_facet | Havaldar, Shreya Alvari, Hamidreza Palowitch, John Hosseini, Mohammad Javad Buthpitiya, Senaka Fabrikant, Alex |
| contents | Much of human communication depends on implication, conveying meaning beyond literal words to express a wider range of thoughts, intentions, and feelings. For models to better understand and facilitate human communication, they must be responsive to the text's implicit meaning. We focus on Natural Language Inference (NLI), a core tool for many language tasks, and find that state-of-the-art NLI models and datasets struggle to recognize a range of cases where entailment is implied, rather than explicit from the text. We formalize implied entailment as an extension of the NLI task and introduce the Implied NLI dataset (INLI) to help today's LLMs both recognize a broader variety of implied entailments and to distinguish between implicit and explicit entailment. We show how LLMs fine-tuned on INLI understand implied entailment and can generalize this understanding across datasets and domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07719 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Entailed Between the Lines: Incorporating Implication into NLI Havaldar, Shreya Alvari, Hamidreza Palowitch, John Hosseini, Mohammad Javad Buthpitiya, Senaka Fabrikant, Alex Computation and Language Much of human communication depends on implication, conveying meaning beyond literal words to express a wider range of thoughts, intentions, and feelings. For models to better understand and facilitate human communication, they must be responsive to the text's implicit meaning. We focus on Natural Language Inference (NLI), a core tool for many language tasks, and find that state-of-the-art NLI models and datasets struggle to recognize a range of cases where entailment is implied, rather than explicit from the text. We formalize implied entailment as an extension of the NLI task and introduce the Implied NLI dataset (INLI) to help today's LLMs both recognize a broader variety of implied entailments and to distinguish between implicit and explicit entailment. We show how LLMs fine-tuned on INLI understand implied entailment and can generalize this understanding across datasets and domains. |
| title | Entailed Between the Lines: Incorporating Implication into NLI |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.07719 |