Saved in:
Bibliographic Details
Main Authors: Prashanth, USVSN Sai, Deng, Alvin, O'Brien, Kyle, S V, Jyothir, Khan, Mohammad Aflah, Borkar, Jaydeep, Choquette-Choo, Christopher A., Fuehne, Jacob Ray, Biderman, Stella, Ke, Tracy, Lee, Katherine, Saphra, Naomi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.17746
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915276633669632
author Prashanth, USVSN Sai
Deng, Alvin
O'Brien, Kyle
S V, Jyothir
Khan, Mohammad Aflah
Borkar, Jaydeep
Choquette-Choo, Christopher A.
Fuehne, Jacob Ray
Biderman, Stella
Ke, Tracy
Lee, Katherine
Saphra, Naomi
author_facet Prashanth, USVSN Sai
Deng, Alvin
O'Brien, Kyle
S V, Jyothir
Khan, Mohammad Aflah
Borkar, Jaydeep
Choquette-Choo, Christopher A.
Fuehne, Jacob Ray
Biderman, Stella
Ke, Tracy
Lee, Katherine
Saphra, Naomi
contents Memorization in language models is typically treated as a homogenous phenomenon, neglecting the specifics of the memorized data. We instead model memorization as the effect of a set of complex factors that describe each sample and relate it to the model and corpus. To build intuition around these factors, we break memorization down into a taxonomy: recitation of highly duplicated sequences, reconstruction of inherently predictable sequences, and recollection of sequences that are neither. We demonstrate the usefulness of our taxonomy by using it to construct a predictive model for memorization. By analyzing dependencies and inspecting the weights of the predictive model, we find that different factors influence the likelihood of memorization differently depending on the taxonomic category.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17746
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
Prashanth, USVSN Sai
Deng, Alvin
O'Brien, Kyle
S V, Jyothir
Khan, Mohammad Aflah
Borkar, Jaydeep
Choquette-Choo, Christopher A.
Fuehne, Jacob Ray
Biderman, Stella
Ke, Tracy
Lee, Katherine
Saphra, Naomi
Computation and Language
Artificial Intelligence
Memorization in language models is typically treated as a homogenous phenomenon, neglecting the specifics of the memorized data. We instead model memorization as the effect of a set of complex factors that describe each sample and relate it to the model and corpus. To build intuition around these factors, we break memorization down into a taxonomy: recitation of highly duplicated sequences, reconstruction of inherently predictable sequences, and recollection of sequences that are neither. We demonstrate the usefulness of our taxonomy by using it to construct a predictive model for memorization. By analyzing dependencies and inspecting the weights of the predictive model, we find that different factors influence the likelihood of memorization differently depending on the taxonomic category.
title Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.17746