Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations

arXiv:2403.06009v1 Announce Type: new
Abstract: Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy a library of detectors: compact and easy-to-build …

abstract api arxiv availability constraints cost cs.lg data etc language language models large language large language models limitations llms risks safety training type