Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, JoonHo, Son, JuYoun, Seok, Juree, Jang, Wooseok, Kwon, Yeong-Dae
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2408.12799
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929692894822400
author Lee, JoonHo
Son, JuYoun
Seok, Juree
Jang, Wooseok
Kwon, Yeong-Dae
author_facet Lee, JoonHo
Son, JuYoun
Seok, Juree
Jang, Wooseok
Kwon, Yeong-Dae
contents Inconsistent annotations in training corpora, particularly within preference learning datasets, pose challenges in developing advanced language models. These inconsistencies often arise from variability among annotators and inherent multi-dimensional nature of the preferences. To address these issues, we introduce a self-curation method that preprocesses annotated datasets by leveraging proxy models trained directly on them. Our method enhances preference learning by automatically detecting and selecting consistent annotations. We validate the proposed approach through extensive instruction-following tasks, demonstrating performance improvements of up to 33\% across various learning algorithms and proxy capabilities. This work offers a straightforward and reliable solution to address preference inconsistencies without relying on heuristics, serving as an initial step toward the development of more advanced preference learning methodologies. Code is available at https://github.com/Self-Curation/ .
format Preprint
id arxiv_https___arxiv_org_abs_2408_12799
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora
Lee, JoonHo
Son, JuYoun
Seok, Juree
Jang, Wooseok
Kwon, Yeong-Dae
Computation and Language
Artificial Intelligence
Inconsistent annotations in training corpora, particularly within preference learning datasets, pose challenges in developing advanced language models. These inconsistencies often arise from variability among annotators and inherent multi-dimensional nature of the preferences. To address these issues, we introduce a self-curation method that preprocesses annotated datasets by leveraging proxy models trained directly on them. Our method enhances preference learning by automatically detecting and selecting consistent annotations. We validate the proposed approach through extensive instruction-following tasks, demonstrating performance improvements of up to 33\% across various learning algorithms and proxy capabilities. This work offers a straightforward and reliable solution to address preference inconsistencies without relying on heuristics, serving as an initial step toward the development of more advanced preference learning methodologies. Code is available at https://github.com/Self-Curation/ .
title Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2408.12799