2025/08/20 by Shubham Pundhir, Pundhir, Shubham, Ganesh Bagler +1
Arts and Humanities · Social Sciences · #Computation and Language (cs.CL) #Digital Games and Media #Digital Humanities and Scholarship #FOS: Computer and information sciences
paper · pdf · doi:10.48550/arxiv.2508.14718
openalex publication_date 2025/08/20 · openalex created_date 2025/10/16 · openalex updated_date 2026/07/28
We established a rigorous benchmark for text-based recipe generation, a fundamental task in natural language generation. We present a comprehensive comparative study contrasting a fine-tuned GPT-2 large (774M) model against the GPT-2 small (124M) model and traditional LSTM/RNN baselines on the 5-cuisine corpus from RecipeDB. Our key contribution is a targeted tokenization strategy that augments the vocabulary with 23 common fraction tokens and custom structural markers. This approach addresses a critical limitation of generic tokenizers by preserving essential recipe structures and precise numerical quantities, thereby enhancing domain specificity. Performance is evaluated using a comprehensive suite of seven automatic metrics spanning fluency (BLEU-4, METEOR), coherence (ROUGE-L), semantic relevance (BERTScore), and diversity. Our experiments show that the large transformer-based approach yields a >20% relative improvement in BERTScore (F1) (0.92 vs 0.72) over the best recurrent baseline, while reducing perplexity by 69.8%. We conclude with a discussion of remaining challenges, particularly regarding factual accuracy, and outline how this foundational study paves the way for integrating real-world constraints and multi-modal inputs in advanced recipe generation research.