Skip to content
NewA calmer, faster ZeroHour

PAIR-MED alternates policy and reward training for medical reasoning

Original title: PAIR-MED: Policy-reward Alternation for Iterative Refinement in Multilingual Medical Reasoning

arXiv cs.AI / cs.LG / cs.CLby Fan Gao ()1 min read1 · 1 read
AI summary · x-ai/grok-4.7Summaries by Vani AI

8B and 9B models across 12 languages lift medical-subset accuracy by 3.01 to 7.47 percent over matching Qwen backbones.

The authors argue a fixed process reward model drifts from an evolving policy during reinforcement learning. PAIR-MED alternates updates: the policy generates multilingual trajectories that retrain a medical process reward model, which then scores the next policy update. After supervised initialization, medical step supervision keeps the reward model grounded while process, outcome, and language rewards guide the policy. PAIR-PRM and PAIR-MED are trained at 8B and 9B scales across 12 languages.

Key facts
  • Gains are reported on medical subsets of Global-MMLU and MMLU-ProX.
  • PAIR-MED-9B raises a joint consistency and accuracy metric by 12.88 percent in-domain on CUREMED-BENCH.
  • The same metric rises 7.45 percent for out-of-domain languages.
  • Analyses cover PRM adaptation and the contribution of each training component.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

Large language models demonstrate strong medical question-answering capabilities, yet reasoning performance remains uneven across languages. Process reward models (PRMs) provide step-level feedback for improving reasoning, but a fixed PRM may become increasingly misaligned with the trajectory distribution of an evolving policy during reinforcement learning, thereby reducing the reliability of its supervision.

arXiv cs.AI / cs.LG / cs.CL

By Fan Gao · arxiv.org

Read the full article at arXiv cs.AI / cs.LG / cs.CL

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.