Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models
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_ | 1866910853615321088 |
|---|---|
| author | Mohan, Jayanth Chowdhury, Jishnu Ray Malik, Tomas Caragea, Cornelia |
| author_facet | Mohan, Jayanth Chowdhury, Jishnu Ray Malik, Tomas Caragea, Cornelia |
| contents | Keyphrases are the essential topical phrases that summarize a document. Keyphrase generation is a long-standing NLP task for automatically generating keyphrases for a given document. While the task has been comprehensively explored in the past via various models, only a few works perform some preliminary analysis of Large Language Models (LLMs) for the task. Given the impact of LLMs in the field of NLP, it is important to conduct a more thorough examination of their potential for keyphrase generation. In this paper, we attempt to meet this demand with our research agenda. Specifically, we focus on the zero-shot capabilities of open-source instruction-tuned LLMs (Phi-3, Llama-3) and the closed-source GPT-4o for this task. We systematically investigate the effect of providing task-relevant specialized instructions in the prompt. Moreover, we design task-specific counterparts to self-consistency-style strategies for LLMs and show significant benefits from our proposals over the baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00597 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models Mohan, Jayanth Chowdhury, Jishnu Ray Malik, Tomas Caragea, Cornelia Computation and Language Artificial Intelligence Keyphrases are the essential topical phrases that summarize a document. Keyphrase generation is a long-standing NLP task for automatically generating keyphrases for a given document. While the task has been comprehensively explored in the past via various models, only a few works perform some preliminary analysis of Large Language Models (LLMs) for the task. Given the impact of LLMs in the field of NLP, it is important to conduct a more thorough examination of their potential for keyphrase generation. In this paper, we attempt to meet this demand with our research agenda. Specifically, we focus on the zero-shot capabilities of open-source instruction-tuned LLMs (Phi-3, Llama-3) and the closed-source GPT-4o for this task. We systematically investigate the effect of providing task-relevant specialized instructions in the prompt. Moreover, we design task-specific counterparts to self-consistency-style strategies for LLMs and show significant benefits from our proposals over the baselines. |
| title | Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.00597 |