Neuro-Symbolic Reasoning
A hybrid AI paradigm that combines the perceptual capabilities of neural networks with the logical reasoning capabilities of symbolic systems. Typical implementations include two paths: symbol extraction followed by reasoning, and regularization through logical constraints.
Timeline (last 90 days)
NARS (Neuro-symbolic Argumentation Reasoning System) is a framework that uses neuro-symbolic hybrid reasoning to directly detect persuasiveness in online discussions, composed of two layers: a neural component (retrieval-augmented iterative LLM reasoning that extracts bipolar argumentation structures) and a symbolic component (gradual argumentation semantics that propagates argument influence).
LLMs are good at extracting structure from messy natural language, but reasoning on top of that structure is better suited to formal methods to guarantee interpretability and consistency.
All Facts (2)
NARS (Neuro-symbolic Argumentation Reasoning System) is a framework that uses neuro-symbolic hybrid reasoning to directly detect persuasiveness in online discussions, composed of two layers: a neural component (retrieval-augmented iterative LLM reasoning that extracts bipolar argumentation structures) and a symbolic component (gradual argumentation semantics that propagates argument influence).
50%UnverifiedLLMs are good at extracting structure from messy natural language, but reasoning on top of that structure is better suited to formal methods to guarantee interpretability and consistency.
50%