CroCoSyn: A Cross-Lingual and Cross-Model Corpus of LLM-Generated Film Synopses
(2026)
Files
crocosyn_paper_escouflaire_EACL.pdf
Open Access - Adobe PDF
- 1.94 MB
Details
- Authors
- Abstract
- (en) We introduce CroCoSyn, a controlled, cross-lingual and cross-model corpus of 25,920 LLM-generated film synopses in English and French. Each synopsis is generated under systematically varied conditions, including model type, temperature, genre, protagonist gender, and narrative constraints, and enriched with struc-tured metadata capturing characters and their relationships. Comparing Mistral and Llama across different model temperature degrees, CroCoSyn enables fine-grained analysis of narrative content, style, and character representation across models and languages. The corpus supports research on gender and cultural biases and story generation evaluation, and provides a foundation for comparative studies between LLM-generated and human-written narratives.
- Affiliations
Citations
Escouflaire, L. (2026). CroCoSyn: A Cross-Lingual and Cross-Model Corpus of LLM-Generated Film Synopses. https://doi.org/10.18653/v1/2026.latechclfl-1.4