arXiv (All)
open access
Scaling Laws for Generative Reward Models
We study generative reward models (GenRMs) as online preference providers for policy optimization in creative writing. Across Qwen3 reward-model sizes from 0.6B to 14B, Thinking judges trained with GRPO have higher static Gold-label accuracy than Answer-Only judges trained with SFT. This ranking oft
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Judging the Justification: Decision Certificate Supervision for Generative Reward Models#1403324
- EnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans#1201383
- DiT-Reward: Generative Representations for Text-to-Image Reward Modeling#299927
- Large Language Models Hack Rewards, and Society#1129288
- The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment#1116348
Record · ID 1423556
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive