Exploring Inference Patterns of LLMs as Symbolic Interactions
Lei Cheng, Wen Shen, Quan-Shi Zhang et al.
· 0 citations
We have 2 of 9 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
It is shown that across a broad class of ANNs trained on diverse tasks, their inference logic can indeed be reformulated as sparse symbolic interactions, and two common mathematical criteria lead to the emergence of such sparse symbolic interactions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.