Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yeh, Min-Hsuan, Wang, Jeffrey, Du, Xuefeng, Park, Seongheon, Tao, Leitian, Im, Shawn, Li, Yixuan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.01957
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918005897691136
author Yeh, Min-Hsuan
Wang, Jeffrey
Du, Xuefeng
Park, Seongheon
Tao, Leitian
Im, Shawn
Li, Yixuan
author_facet Yeh, Min-Hsuan
Wang, Jeffrey
Du, Xuefeng
Park, Seongheon
Tao, Leitian
Im, Shawn
Li, Yixuan
contents As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignment methods primarily focus on designing algorithms and loss functions but often underestimate the crucial role of data. This paper advocates for a shift towards data-centric AI alignment, emphasizing the need to enhance the quality and representativeness of data used in aligning AI systems. In this position paper, we highlight key challenges associated with both human-based and AI-based feedback within the data-centric alignment framework. Through qualitative analysis, we identify multiple sources of unreliability in human feedback, as well as problems related to temporal drift, context dependence, and AI-based feedback failing to capture human values due to inherent model limitations. We propose future research directions, including improved feedback collection practices, robust data-cleaning methodologies, and rigorous feedback verification processes. We call for future research into these critical directions to ensure, addressing gaps that persist in understanding and improving data-centric alignment practices.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Challenges and Future Directions of Data-Centric AI Alignment
Yeh, Min-Hsuan
Wang, Jeffrey
Du, Xuefeng
Park, Seongheon
Tao, Leitian
Im, Shawn
Li, Yixuan
Computation and Language
As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignment methods primarily focus on designing algorithms and loss functions but often underestimate the crucial role of data. This paper advocates for a shift towards data-centric AI alignment, emphasizing the need to enhance the quality and representativeness of data used in aligning AI systems. In this position paper, we highlight key challenges associated with both human-based and AI-based feedback within the data-centric alignment framework. Through qualitative analysis, we identify multiple sources of unreliability in human feedback, as well as problems related to temporal drift, context dependence, and AI-based feedback failing to capture human values due to inherent model limitations. We propose future research directions, including improved feedback collection practices, robust data-cleaning methodologies, and rigorous feedback verification processes. We call for future research into these critical directions to ensure, addressing gaps that persist in understanding and improving data-centric alignment practices.
title Challenges and Future Directions of Data-Centric AI Alignment
topic Computation and Language
url https://arxiv.org/abs/2410.01957