Abstract
Large Language Models (LLMs) have seen a surge in popularity due to their impressive results in natural language processing tasks, but there are still challenges to be addressed. Prompting in the question is a solution for some of them. In this paper, we present PIQARD, an open-source Python library that allows researchers to experiment with prompting techniques and information retrieval, and combine them with LLMs. This library includes pre-implemented components and also allows users to integrate their own methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
PIQARD is an acronym from Prompted Intelligent Question Answering with Retrieval of Documents.
- 2.
More information about the library, examples of its use as well as a video presentation are available at PIQARD GitHub website https://plaskod.github.io/.
References
Reppert, J., et al.: Iterated Decomposition: Improving Science Q &A by Supervising Reasoning Processes. arXiv:2301.01751
OpenAI GPT-4 Technical Report. arXiv:2303.08774
Chase, H.: LangChain (2022). https://github.com/hwchase17/langchain
Acknowledgements
The research was partially supported by SBAD/0740 grant.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Korcz, M., Plaskowski, D., Politycki, M., Stefanowski, J., Terentowicz, A. (2023). PIQARD System for Experimenting and Testing Language Models with Prompting Strategies. In: De Francisci Morales, G., Perlich, C., Ruchansky, N., Kourtellis, N., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14175. Springer, Cham. https://doi.org/10.1007/978-3-031-43430-3_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-43430-3_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43429-7
Online ISBN: 978-3-031-43430-3
eBook Packages: Computer ScienceComputer Science (R0)