SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning

Documenti analoghi

• Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
  di: Liu, Hanbing, et al.
  Pubblicazione: (2025)
• TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models
  di: Yi, Deyin, et al.
  Pubblicazione: (2025)
• Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning
  di: Cao, Lang, et al.
  Pubblicazione: (2025)
• Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search
  di: Li, Shuocheng, et al.
  Pubblicazione: (2025)
• TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models
  di: He, Xinyi, et al.
  Pubblicazione: (2025)