mlsanityData to 14 Oct 2026

Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models

arXiv 2503.00597 ↗First posted 1 Mar 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 66 references that are in the map. First posted on arXiv 1 Mar 2025.

Builds on

34 of 66 references.

References · 34

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  6. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 236
  7. 2017SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publicationscited by 102
  8. 2017Deep Keyphrase Generationcited by 102
  9. 2018Simple Unsupervised Keyphrase Extraction using Sentence Embeddingscited by 62
  10. 2018One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrasescited by 52
  11. 2018Keyphrase Generation with Correlation Constraintscited by 45
  12. 2019Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewardscited by 41
22 more
  1. 2019KPTimes: A Large-Scale Dataset for Keyphrase Generation on News Documentscited by 41
  2. 2021One2Set: Generating Diverse Keyphrases as a Setcited by 41
  3. 2020Exclusive Hierarchical Decoding for Deep Keyphrase Generationcited by 38
  4. 2018Semi-Supervised Learning for Neural Keyphrase Generationcited by 36
  5. 2021Learning Rich Representation of Keyphrases from Textcited by 36
  6. 2021Keyphrase Generation for Scientific Document Retrievalcited by 23
  7. 2023Is ChatGPT A Good Keyphrase Generator? A Preliminary Studycited by 17
  8. 2021UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Predictioncited by 15
  9. 2021Heterogeneous Graph Neural Networks for Keyphrase Generationcited by 15
  10. 2022Representation Learning for Resource-Constrained Keyphrase Generationcited by 14
  11. 2020Keyphrase Prediction With Pre-trained Language Modelcited by 13
  12. 2022Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Studycited by 13
  13. 2023ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Taskcited by 13
  14. 2019Keyphrase Extraction from Disaster-related Tweetscited by 12
  15. 2021Keyphrase Generation Beyond the Boundaries of Title and Abstractcited by 12
  16. 2023Data Augmentation for Low-Resource Keyphrase Generationcited by 8
  17. 2023Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Modelscited by 8
  18. 2022Conditional set generation using Seq2seq modelscited by 7
  19. 2023SimCKP: Simple Contrastive Learning of Keyphrase Representationscited by 4
  20. 2023Large Language Models as Zero-Shot Keyphrase Extractors: A Preliminary Empirical Studycited by 4
  21. 2024On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generationcited by 3
  22. 2018WikiRank: Improving Keyphrase Extraction Based on Background Knowledgecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024MetaKP: On-Demand Keyphrase Generation
  2. 2022Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training
  3. 2024Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
  4. 2024Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation
  5. 2025MAPEX: A Multi-Agent Pipeline for Keyphrase Extraction
  6. 2023Vector-Quantized Prompt Learning for Paraphrase Generation
  7. 2023Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task
  8. 2025From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding