LLM Harms: A Taxonomy and Discussion
Kevin Chen, Saleh Afroogh, Abhejay Murali, David Atkinson, Amit Dhurandhar, Junfeng Jiao

TL;DR
This paper categorizes potential harms of Large Language Models across development and deployment stages, emphasizing the need for accountability, transparency, and mitigation strategies to ensure responsible AI integration.
Contribution
It provides a comprehensive taxonomy of LLM harms, discusses mitigation strategies, and proposes a dynamic auditing system for responsible development and deployment.
Findings
Identifies five key harm categories in LLM lifecycle.
Highlights the importance of transparency and bias mitigation.
Proposes a standardized auditing framework for LLMs.
Abstract
This study addresses categories of harm surrounding Large Language Models (LLMs) in the field of artificial intelligence. It addresses five categories of harms addressed before, during, and after development of AI applications: pre-development, direct output, Misuse and Malicious Application, and downstream application. By underscoring the need to define risks of the current landscape to ensure accountability, transparency and navigating bias when adapting LLMs for practical applications. It proposes mitigation strategies and future directions for specific domains and a dynamic auditing system guiding responsible development and integration of LLMs in a standardized proposal.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
