Neurosymbolic artificial intelligence via large language models and coherence-driven inference

Abstract: We devise an algorithm to generate sets of propositions that objectively instantiate graphs that support coherence-driven inference. We then benchmark the ability of LLMs to reconstruct coherence graphs from (a straightforward transformation of) propositions expressed in natural language, with promising results from a single prompt to models optimized for reasoning. Combining coherence-driven inference with consistency evaluations by neural models may advance the state of the art in machine cognition.