Formalizing content creation and evaluation methods for AI-generated social media content

Christian Jensen, Axel Højmark


Abstract
This study explores the use of large language models (LLMs), such as ChatGPT and GPT-4, in creating high-quality text-based social media content for businesses on LinkedIn. We introduce a novel architecture incorporating external knowledge bases and a multi-step writing approach, which extracts facts from company websites to form a knowledge graph. Our method’s efficacy is assessed using the “Long-LinkedIn” evaluation dataset designed for long-form post generation. Results indicate that our iterative refinement significantly improves content quality. However, knowledge-enhanced prompts occasionally reduced quality due to potential formulation issues. LLM-based evaluations, particularly using ChatGPT, showcased potential as a less resource-intensive alternative to human assessments, with a notable alignment between the two evaluation techniques.
Anthology ID:
2023.gem-1.3
Volume:
Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
Month:
December
Year:
2023
Address:
Singapore
Editors:
Sebastian Gehrmann, Alex Wang, João Sedoc, Elizabeth Clark, Kaustubh Dhole, Khyathi Raghavi Chandu, Enrico Santus, Hooman Sedghamiz
Venues:
GEM | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22–41
Language:
URL:
https://aclanthology.org/2023.gem-1.3
DOI:
Bibkey:
Cite (ACL):
Christian Jensen and Axel Højmark. 2023. Formalizing content creation and evaluation methods for AI-generated social media content. In Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 22–41, Singapore. Association for Computational Linguistics.
Cite (Informal):
Formalizing content creation and evaluation methods for AI-generated social media content (Jensen & Højmark, GEM-WS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2023.gem-1.3.pdf
Supplementary material:
 2023.gem-1.3.SupplementaryMaterial.zip