Current state of LLM Risks and AI Guardrails

arXiv:2406.12934v1 Announce Type: new
Abstract: Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias, potential for unsafe actions, dataset poisoning, lack of explainability, hallucinations, and non-reproducibility. These risks necessitate the development of "guardrails" to align LLMs with desired behaviors and mitigate potential harm.
This work explores the risks associated with deploying LLMs and evaluates current approaches to implementing guardrails …

actions applications arxiv bias cs.ai cs.cr cs.hc current dataset deployment development explainability guardrails hallucinations language language models large llm llms non paramount poisoning reliability risks safety sensitive state