ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training

Documenti analoghi

• Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
  di: Ai, Rui, et al.
  Pubblicazione: (2025)
• LLM Evaluation as Tensor Completion: Low Rank Structure and Semiparametric Efficiency
  di: Li, Jiachun, et al.
  Pubblicazione: (2026)
• OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents
  di: Ao, Ruicheng, et al.
  Pubblicazione: (2026)
• ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values
  di: Bewley, Tom, et al.
  Pubblicazione: (2026)
• DistShap: Scalable GNN Explanations with Distributed Shapley Values
  di: Akkas, Selahattin, et al.
  Pubblicazione: (2025)