← Back to the wire

Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering

AchievementResearchJul 9, 2026

Felix Feldman extended PubHealthBench into a retrieval-augmented setting, evaluating retrieval and generation choices across 7,929 public health questions. Hybrid retrieval consistently improved recall and ranking quality, while retrieved context substantially increased multiple-choice accuracy, enabling smaller open-weight models to match or outperform larger models without retrieval. A rubric-based LLM-as-a-judge assessed free-form answering, with strongest human agreement on faithfulness and completeness.

Receipt № 4811 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01medPRIMARY
Felix FeldmanPerson
Canonical: https://arxiv.org/abs/2607.06641