Papers
Topics
Authors
Recent
2000 character limit reached

Designing Informative Metrics for Few-Shot Example Selection (2403.03861v3)

Published 6 Mar 2024 in cs.CL and cs.LG

Abstract: Pretrained LLMs (PLMs) have shown remarkable few-shot learning capabilities when provided with properly formatted examples. However, selecting the "best" examples remains an open challenge. We propose a complexity-based prompt selection approach for sequence tagging tasks. This approach avoids the training of a dedicated model for selection of examples, and instead uses certain metrics to align the syntactico-semantic complexity of test sentences and examples. We use both sentence- and word-level metrics to match the complexity of examples to the (test) sentence being considered. Our results demonstrate that our approach extracts greater performance from PLMs: it achieves state-of-the-art performance on few-shot NER, achieving a 5% absolute improvement in F1 score on the CoNLL2003 dataset for GPT-4. We also see large gains of upto 28.85 points (F1/Acc.) in smaller models like GPT-j-6B.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (16)
  1. Dhananjay Ashok and Zachary C. Lipton. 2023. Promptner: Prompting for named entity recognition.
  2. Prompting language models for linguistic structure.
  3. Language models are few-shot learners.
  4. How is chatgpt’s behavior changing over time?
  5. What makes good in-context examples for GPT-3? In Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, pages 100–114, Dublin, Ireland and Online. Association for Computational Linguistics.
  6. Rethinking the role of demonstrations: What makes in-context learning work?
  7. Universal Dependencies v2: An evergrowing multilingual treebank collection. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4034–4043, Marseille, France. European Language Resources Association.
  8. Learning to retrieve prompts for in-context learning.
  9. Quantifying language models’ sensitivity to spurious features in prompt design or: How i learned to start worrying about prompt formatting. In The Twelfth International Conference on Learning Representations.
  10. Beyond the text: Analysis of privacy statements through syntactic and semantic role labeling. In Proceedings of the Natural Legal Language Processing Workshop 2023, pages 85–98, Singapore. Association for Computational Linguistics.
  11. Going against the (appropriate) flow: A contextual integrity approach to privacy policy analysis. In AAAI Conference on Human Computation & Crowdsourcing.
  12. An information-theoretic approach to prompt engineering without ground truth labels. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics.
  13. Erik F. Tjong Kim Sang and Sabine Buchholz. 2000. Introduction to the CoNLL-2000 shared task chunking. In Fourth Conference on Computational Natural Language Learning and the Second Learning Language in Logic Workshop.
  14. Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142–147.
  15. Chain-of-thought prompting elicits reasoning in large language models.
  16. Amir Zeldes. 2017. The gum corpus: creating multilayer resources in the classroom. Lang. Resour. Eval., 51(3):581–612.
Citations (1)

Summary

We haven't generated a summary for this paper yet.

Whiteboard

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.