# Losses that Cook: Topological Optimal Transport for Structured Recipe Generation

arXiv: https://arxiv.org/abs/2601.02531 · HTML: https://mlsanity.com/paper/2601.02531/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 24 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Builds on (most cited first, 4 of 4)

- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [A Smoothed Dual Approach for Variational Wasserstein Problems](https://mlsanity.com/paper/1503.02533/) (2015)
- [Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning](https://mlsanity.com/paper/2409.13641/) (2024)

## Abstract (arXiv)

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 NLG metrics and recipe-specific metrics, we find that our loss significantly improves ingredient- and action-level 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.