Evaluation of four general-purpose LLMs on FoodBench tasks shows limited performance across nutrient estimation, traffic-light classification, and food interoperability, even with few-shot prompting, highlighting the need for domain-specialized LLMs fine-tuned on food data.
T. Eftimov, Ana Gjorgjevikj, M. Martinc et al.· Scientific Data· 1 citation
Multi-kernel clustering over heterogeneous landscape representations obtains the strongest mean profile on the DE portfolio and remains competitive with, and nominally ahead of, the leading baselines on the more compressed PSO portfolio, where differences among the best methods are small relative to stochastic variatio...
Yi-Hang Lu, T. Eftimov, C. Doerr· arXiv.org· 0 citations
A two-dimensional framework, specifically tailored for analyzing multilingual embedding benchmarks under dataset scarcity, is proposed and applied on the Slavic-language subset of the MTEB benchmark, revealing severe benchmark sparsity.
Ana Gjorgjevikj, B. Seljak, T. Eftimov· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.