2023 · 75 citations · 44 references
ComputingArchaeologyComputer ScienceData MiningKnowledge RepresentationNatural Language ProcessingKnowledge AcquisitionKnowledge RetrievalLanguage ModelingSource MemoryText CollectionCultural Heritage AnalyticsCuration Of Archaeological CollectionsOpen ArchaeologyPerformance Measurement Validity
In this work, we carry out a data archaeology to infer books that are known to ChatGPT and GPT-4 using a name cloze membership inference query. We find that OpenAI models have memorized a wide collection of copyrighted materials, and that the degree of memorization is tied to the frequency with which passages of those books appear on the web. The ability of these models to memorize an unknown set of books complicates assessments of measurement validity for cultural analytics by contaminating test data; we show that models perform much better on memorized books than on non-memorized books for downstream tasks. We argue that this supports a case for open models whose training data is known.
44
Distinction: A Social Critique of the Judgement of Taste.
M. Warner, Pierre Bourdıeu, Richard Nice · MLN · 1985 · 14.2K citations
Membership Inference Attacks Against Machine Learning Models
Reza Shokri, Marco Stronati, Congzheng Song et al. · 2017 · 4.2K citations
LLaMA: Open and Efficient Foundation Language Models
Hugo Touvron, Thibaut Lavril, Gautier Izacard et al. · arXiv (Cornell University) · 2023 · 3.9K citations · Full text
Yukun Zhu, Ryan Kiros, Rich Zemel et al. · 2015 · 2.1K citations · Full text