AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking

Documenti analoghi

• R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
  di: Chen, Yongchao, et al.
  Pubblicazione: (2025)
• Speaking in Words, Thinking in Logic: A Dual-Process Framework in QA Systems
  di: Bui, Tuan, et al.
  Pubblicazione: (2025)
• LLMs as mirrors of societal moral standards: reflection of cultural divergence and agreement across ethical topics
  di: Meijer, Mijntje, et al.
  Pubblicazione: (2024)
• Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making
  di: Wu, Siyu, et al.
  Pubblicazione: (2024)
• Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning
  di: Hersche, Michael, et al.
  Pubblicazione: (2024)