SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment

Documenti analoghi

• Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data
  di: Yixuan, Deng, et al.
  Pubblicazione: (2025)
• Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models
  di: Tang, Yixuan, et al.
  Pubblicazione: (2026)
• Personality Alignment of Large Language Models
  di: Zhu, Minjun, et al.
  Pubblicazione: (2024)
• GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings
  di: Tang, Yixuan, et al.
  Pubblicazione: (2025)
• Process Reward Model with Q-Value Rankings
  di: Li, Wendi, et al.
  Pubblicazione: (2024)