Tracing the Genealogies of Ideas with Large Language Model Embeddings

In this paper, I present a novel method to detect intellectual influence across a large corpus. Taking advantage of the unique affordances of large language models in encoding semantic and structural meaning while remaining robust to paraphrasing, we can search for substantively similar ideas and hints of intellectual influence in a computationally efficient manner. Such a method allows us to operationalize different levels of confidence: we can allow for direct quotation, paraphrase, or speculative similarity while remaining open about the …

cs.cl cs.si embeddings encoding ideas influence language language model language models large language large language model large language models meaning novel paper paraphrasing robust search semantic tracing