# Tracing the Genealogies of Ideas with Large Language Model Embeddings

arXiv: https://arxiv.org/abs/2402.01661 · HTML: https://mlsanity.com/paper/2402.01661/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 13 Jan 2024.

## Builds on (most cited first, 7 of 7)

- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [BioSentVec: creating sentence embeddings for biomedical texts](https://mlsanity.com/paper/1810.09302/) (2018)
- [AMR Similarity Metrics from Principles](https://mlsanity.com/paper/2001.10929/) (2020)
- [Individuals, Institutions, and Innovation in the Debates of the French Revolution](https://mlsanity.com/paper/1710.06867/) (2017)
- [Abolitionist Networks: Modeling Language Change in Nineteenth-Century Activist Newspapers](https://mlsanity.com/paper/2103.07538/) (2021)
- [The Cultural Evolution of National Constitutions](https://mlsanity.com/paper/1711.06899/) (2017)
- [Self-citation Analysis using Sentence Embeddings](https://mlsanity.com/paper/2105.05527/) (2021)

## Abstract (arXiv)

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 limitations of each threshold. I apply an ensemble method combining General Text Embeddings, a state-of-the-art sentence embedding method optimized to capture semantic content and an Abstract Meaning Representation graph representation designed to capture structural similarities in argumentation style and the use of metaphor. I apply this method to vectorize sentences from a corpus of roughly 400,000 nonfiction books and academic publications from the 19th century for instances of ideas and arguments appearing in Darwin's publications. This functions as an initial evaluation and proof of concept; the method is not limited to detecting Darwinian ideas but is capable of detecting similarities on a large scale in a wide range of corpora and contexts.