RESEARCH · RESEARCH · #2983
Noura: specification-guided supervision markedly improves LLM dietary planning
arXiv:2610.40992v1 introduces Noura, a system that pairs LLM planning with executable personal specifications derived from public clinical guidance and individual health/dietary profiles to generate and iteratively correct multi-day meal plans. In a dietitian-approved NHANES-based weekly planning evaluation (4,993 held-out participants), thirteen baseline models pass fewer than 3% of complete plans by direct generation; Noura-SFT raises Qwen3-14B's complete-plan pass rate from 24.0% to 72.5%, cuts rule violations by 97.5% with no observed critical failures, shows a locally hosted 14B planner with fewer violations than a GPT-6 Luna teacher, and reports executed-target and self-training gains that reduce rule violations by 41–61% across Qwen, Phi, and Llama backbones.
KEY POINTS
- arXiv:2610.40992v1 introduces Noura, a system that pairs LLM planning with executable personal specifications derived from public clinical guidance and individual health/dietary profiles to generate and iteratively correct multi-day meal plans.
- In a dietitian-approved NHANES-based weekly planning evaluation (4,993 held-out participants), thirteen baseline models pass fewer than 3% of complete plans by direct generation; Noura-SFT raises Qwen3-14B's complete-plan pass rate from 24.0% to 72.5%, cuts rule violations by 97.5% with no observed critical failures, shows a locally hosted 14B planner with fewer violations than a GPT-6 Luna teacher, and reports executed-target and self-training gains that reduce rule violations by 41–61% across Qwen, Phi, and Llama backbones.
- This shows executable, personalized specifications can convert public clinical rules into effective supervision and self-training signals that substantially improve compact LLM planners' correctness and safety in sensitive planning tasks.
WHY IT MATTERS
This shows executable, personalized specifications can convert public clinical rules into effective supervision and self-training signals that substantially improve compact LLM planners' correctness and safety in sensitive planning tasks.