Natural Language Reference Representations to Tabular Input Representations
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This dataset contains prompts and corresponding generated natural language texts by multiple versions of GPT. The prompts ask to invent a person matching a given feature set (input representation) from the German Credit Dataset and to generate a loan application letter from the perspective of this fictional person. The text files contain the results of manually reconstructing the input represenation from the generated texts (reference representations).
Fields of Study & Subjects
Topic Modeling
Natural Language Processing Techniques
Multimodal Machine Learning Applications
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 30 March 2026
- Language
- EN
- Document type
- Dataset