Saved in:
Bibliographic Details
Main Authors: Nelson, Jordan, Baimagambetov, Almas, Avgerinakis, Konstantinos, Polatidis, Nikolaos
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.06924
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908784522166272
author Nelson, Jordan
Baimagambetov, Almas
Avgerinakis, Konstantinos
Polatidis, Nikolaos
author_facet Nelson, Jordan
Baimagambetov, Almas
Avgerinakis, Konstantinos
Polatidis, Nikolaos
contents As large language models (LLMs) shape AI development, ensuring ethical prompt recommendations is crucial. LLMs offer innovation but risk bias, fairness issues, and accountability concerns. Traditional oversight methods struggle with scalability, necessitating dynamic solutions. This paper proposes using collaborative filtering, a technique from recommendation systems, to enhance ethical prompt selection. By leveraging user interactions, it promotes ethical guidelines while reducing bias. Contributions include a synthetic dataset for prompt recommendations and the application of collaborative filtering. The work also tackles challenges in ethical AI, such as bias mitigation, transparency, and preventing unethical prompt engineering.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ethical AI prompt recommendations in large language models using collaborative filtering
Nelson, Jordan
Baimagambetov, Almas
Avgerinakis, Konstantinos
Polatidis, Nikolaos
Information Retrieval
As large language models (LLMs) shape AI development, ensuring ethical prompt recommendations is crucial. LLMs offer innovation but risk bias, fairness issues, and accountability concerns. Traditional oversight methods struggle with scalability, necessitating dynamic solutions. This paper proposes using collaborative filtering, a technique from recommendation systems, to enhance ethical prompt selection. By leveraging user interactions, it promotes ethical guidelines while reducing bias. Contributions include a synthetic dataset for prompt recommendations and the application of collaborative filtering. The work also tackles challenges in ethical AI, such as bias mitigation, transparency, and preventing unethical prompt engineering.
title Ethical AI prompt recommendations in large language models using collaborative filtering
topic Information Retrieval
url https://arxiv.org/abs/2510.06924