Large language models for ingredient substitution in food recipes using supervised fine-tuning and direct preference optimization
Thevin Senath; Kumuthu Athukorala; Ransika Costa; Surangika Ranathunga; Rishemjit Kaur · 2025 · Natural Language Processing Journal
WASTE classifies this as Negative / Null Result Report · AI classification, approximate
The study found no significant effect — useful as a negative control or null benchmark for your own design.
Abstract
In this paper, we address the challenge of recipe personalization through ingredient substitution. We make use of Large Language Models (LLMs) to build an ingredient substitution system designed to predict plausible substitute ingredients within a given recipe context. Given that the use of LLMs for this task has been barely done, we carry out an extensive set of experiments to determine the best LLM, prompt, and the fine-tuning setups. We further experiment with methods such as multi-task learning, two-stage fine-tuning, and Direct Preference Optimization (DPO). The experiments are conducted
Abstract by Thevin Senath; Kumuthu Athukorala; Ransika Costa; Surangika Ranathunga; Rishemjit Kaur, Natural Language Processing Journal (2025) — licensed CC BY 4.0.
About to run something similar?
Run an AI Precheck on your own design to catch failure modes like this one before you spend the time. Your first desk check is free.
Related failures
Leakage and the reproducibility crisis in machine-learning-based science
Negative / Null Result ReportDefining and detecting quantum speedup
Negative / Null Result ReportService robots in hotels: understanding the service quality perceptions of human-robot interaction
Negative / Null Result ReportBoosting methods for multi-class imbalanced data classification: an experimental review
Negative / Null Result ReportFINANCIAL DEVELOPMENT AND ECONOMIC GROWTH: A META‐ANALYSIS
Negative / Null Result ReportThe impact of site-specific digital histology signatures on deep learning model accuracy and bias
WASTE indexes this work — it does not host or republish it. Failure-type classification is automated and approximate.
Metadata source: OpenAlex · DOI 10.1016/j.nlp.2025.100177