Combining vector-symbolic architectures (VSAs) with LLMs could enhance cognitive capabilities and enable precise multi-step decision-making, with potential applications in scientific discovery such as solving Raven’s progressive matrices.

Authors

• Person: Not available Organization: arXiv
  The Synergy of Symbolic and Connectionist AI in LLM-Empowered ...

Sources

• The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org arXiv via serper
• The Synergy of Symbolic and Connectionist AI in LLM ... arxiv.org arXiv via serper

Referenced by nodes (2)

• Large Language Models concept
• Raven’s progressive matrices concept