iiinova — where your digital self keeps evolving

gordanaispirova.bsky.social

@gordanaispirova.bsky.social

Reposted by @gordanaispirova.bsky.social

Giulia Menichetti @menicgiulia.bsky.social · 27/05/2025

𝑊ℎ𝑎𝑡 𝑑𝑜𝑒𝑠 𝑖𝑡 𝑟𝑒𝑎𝑙𝑙𝑦 𝑚𝑒𝑎𝑛 𝑓𝑜𝑟 𝑎 𝑓𝑜𝑜𝑑 𝑡𝑜 𝑏𝑒 𝑝𝑟𝑜𝑐𝑒𝑠𝑠𝑒𝑑? We looked for answers through data science. Using multimodal AI models, we show the opportunities and limitations of current approaches. 📄 Read: arxiv.org/abs/2505.17087 💻 Code: github.com/menicgiulia/...

Example instance from the Open Food Facts dataset used in the training of the predictive models. The product name, ingredient list, and full nutrient panel (not fully shown here) are used to construct the input sentences for the LLM-based models. The nutrient panel shown includes the 11 nutrients used to train the FoodProX-based models. The last two quantitative indicators are used in the explanatory models. The number of additives is also included as an additional feature in one variant of the FoodProX model.

111

Reposted by @gordanaispirova.bsky.social

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 26/05/2025

Gordana Ispirova, Michael Sebek, Giulia Menichetti: Informatics for Food Processing arxiv.org/abs/2505.17087 arxiv.org/pdf/2505.17087 arxiv.org/html/2505.17087

116

Reposted by @gordanaispirova.bsky.social

arxiv cs.CL @arxiv-cs-cl.bsky.social · 26/05/2025

Gordana Ispirova, Michael Sebek, Giulia Menichetti Informatics for Food Processing arxiv.org/abs/2505.17087

012