Experimentation in Content Moderation using RWKV

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yildirim, Umut, Dutta, Rohan, Yildirim, Burak, Vaidya, Atharva
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913492734312448
author Yildirim, Umut
Dutta, Rohan
Yildirim, Burak
Vaidya, Atharva
author_facet Yildirim, Umut
Dutta, Rohan
Yildirim, Burak
Vaidya, Atharva
contents This paper investigates the RWKV model's efficacy in content moderation through targeted experimentation. We introduce a novel dataset specifically designed for distillation into smaller models, enhancing content moderation practices. This comprehensive dataset encompasses images, videos, sounds, and text data that present societal challenges. Leveraging advanced Large Language Models (LLMs), we generated an extensive set of responses -- 558,958 for text and 83,625 for images -- to train and refine content moderation systems. Our core experimentation involved fine-tuning the RWKV model, capitalizing on its CPU-efficient architecture to address large-scale content moderation tasks. By highlighting the dataset's potential for knowledge distillation, this study not only demonstrates RWKV's capability in improving the accuracy and efficiency of content moderation systems but also paves the way for developing more compact, resource-efficient models in this domain. Datasets and models can be found in HuggingFace: https://huggingface.co/modrwkv
format Preprint
id arxiv_https___arxiv_org_abs_2409_03939
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Experimentation in Content Moderation using RWKV
Yildirim, Umut
Dutta, Rohan
Yildirim, Burak
Vaidya, Atharva
Computation and Language
68T50
I.2.7
This paper investigates the RWKV model's efficacy in content moderation through targeted experimentation. We introduce a novel dataset specifically designed for distillation into smaller models, enhancing content moderation practices. This comprehensive dataset encompasses images, videos, sounds, and text data that present societal challenges. Leveraging advanced Large Language Models (LLMs), we generated an extensive set of responses -- 558,958 for text and 83,625 for images -- to train and refine content moderation systems. Our core experimentation involved fine-tuning the RWKV model, capitalizing on its CPU-efficient architecture to address large-scale content moderation tasks. By highlighting the dataset's potential for knowledge distillation, this study not only demonstrates RWKV's capability in improving the accuracy and efficiency of content moderation systems but also paves the way for developing more compact, resource-efficient models in this domain. Datasets and models can be found in HuggingFace: https://huggingface.co/modrwkv
title Experimentation in Content Moderation using RWKV
topic Computation and Language
68T50
I.2.7
url https://arxiv.org/abs/2409.03939