benchmark · first seen 7 Oct 2026
HealthBench
A benchmark of physician-written, instance-specific rubrics for evaluating responses to health-related conversations.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Evaluating Rubric Generation with Interventional TransferPapers · 7 Oct 2026 · Erik Skalnes, Layne C. Price, Raviteja Anantha, Michael Oberst
- Safety-Preserving Medical LLM Fine-Tuning via Bilevel Data SelectionPapers · 16 Nov 2026 · Ruoxuan Shi, Sheng Yang, Zhengxing Su, Xiaoyang Hou, Yating Liu
Latest sources
- Safety-Preserving Medical LLM Fine-Tuning via Bilevel Data SelectionPapers · 16 Nov 2026 · Ruoxuan Shi, Sheng Yang, Zhengxing Su, Xiaoyang Hou, Yating Liu
- Evaluating Rubric Generation with Interventional TransferPapers · 7 Oct 2026 · Erik Skalnes, Layne C. Price, Raviteja Anantha, Michael Oberst