Year: 2026
Type: conference-paper
Abstract: Cooking recipes are complex procedures that require not only a fluent and factual text, but also accurate timing, temperature, and procedural coherence, as well as the correct composition of ingredients.Standard training procedures are primarily based on cross-entropy and focus solely on fluency.Building on RECIPE-NLG, we investigate the use of several composite objectives and present a new topological loss that represents ingredient lists as point clouds in embedding space, minimizing the divergence between predicted and gold ingredients.Using both standard language generation metrics and recipe-specific metrics, we find that our loss significantly improves ingredient-and actionlevel metrics.Meanwhile, the Dice loss excels in time/temperature precision, and the mixed loss yields competitive trade-offs with synergistic gains in quantity and time.A human preference analysis supports our finding, showing our model is preferred in 62% of the cases.
Institution: Politecnico di Torino
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166872813