Towards a Programmable Humanizing AI through Scalable Stance-Directed Architecture

Date

2024-01-01

Author

Çetinkaya, Yusuf Mucahit
Lee, Yeonjung
Külah, Emre
Toroslu, İsmail Hakkı
Cowan, Michael A.
Davulcu, Hasan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

37
views

0
downloads

Cite This

The rise of harmful online content underscores the urgent need for AI systems to effectively detect, filter those, and foster safer and healthier communication. This article introduces a novel approach to mitigate toxic content generation propensities of Large Language Models (LLMs) by fine-tuning them with a programmable stance-directed focus on core human values and common good. We propose a streamlined keyword coding and processing pipeline to generate weakly labeled data to train AI models that can avoid toxicity and champion civil discourse. We also developed a toxicity classifier and an Aspect-based Sentiment Analysis (ABSA) model to assess and control the effectiveness of a humanizing AI model. We evaluate the proposed pipeline using a contentious real-world Twitter dataset on U.S. race relations. Our approach successfully curbs the toxic content generation propensity of an unrestricted LLM by a significant 85%.

Subject Keywords

language generation, language models, sentiment analysis, social networking, Twitter, web text analysis

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85203522810&origin=inward
https://hdl.handle.net/11511/111089

Collections

Department of Computer Engineering, Article