On the Way to LLM Personalization: Learning to Remember User Conversations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Magister, Lucie Charlotte, Metcalf, Katherine, Zhang, Yizhe, ter Hoeve, Maartje
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913581962887168
author Magister, Lucie Charlotte
Metcalf, Katherine
Zhang, Yizhe
ter Hoeve, Maartje
author_facet Magister, Lucie Charlotte
Metcalf, Katherine
Zhang, Yizhe
ter Hoeve, Maartje
contents Large Language Models (LLMs) have quickly become an invaluable assistant for a variety of tasks. However, their effectiveness is constrained by their ability to tailor responses to human preferences and behaviors via personalization. Prior work in LLM personalization has largely focused on style transfer or incorporating small factoids about the user, as knowledge injection remains an open challenge. In this paper, we explore injecting knowledge of prior conversations into LLMs to enable future work on less redundant, personalized conversations. We identify two real-world constraints: (1) conversations are sequential in time and must be treated as such during training, and (2) per-user personalization is only viable in parameter-efficient settings. To this aim, we propose PLUM, a pipeline performing data augmentation for up-sampling conversations as question-answer pairs, that are then used to finetune a low-rank adaptation adapter with a weighted cross entropy loss. Even in this first exploration of the problem, we perform competitively with baselines such as RAG, attaining an accuracy of 81.5% across 100 conversations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13405
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Way to LLM Personalization: Learning to Remember User Conversations
Magister, Lucie Charlotte
Metcalf, Katherine
Zhang, Yizhe
ter Hoeve, Maartje
Computation and Language
Machine Learning
Large Language Models (LLMs) have quickly become an invaluable assistant for a variety of tasks. However, their effectiveness is constrained by their ability to tailor responses to human preferences and behaviors via personalization. Prior work in LLM personalization has largely focused on style transfer or incorporating small factoids about the user, as knowledge injection remains an open challenge. In this paper, we explore injecting knowledge of prior conversations into LLMs to enable future work on less redundant, personalized conversations. We identify two real-world constraints: (1) conversations are sequential in time and must be treated as such during training, and (2) per-user personalization is only viable in parameter-efficient settings. To this aim, we propose PLUM, a pipeline performing data augmentation for up-sampling conversations as question-answer pairs, that are then used to finetune a low-rank adaptation adapter with a weighted cross entropy loss. Even in this first exploration of the problem, we perform competitively with baselines such as RAG, attaining an accuracy of 81.5% across 100 conversations.
title On the Way to LLM Personalization: Learning to Remember User Conversations
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.13405