Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
This addresses safety and reliability issues for users and developers of LLMs, but it is incremental as it builds on existing detection approaches.
The paper tackles the problem of risks in large language models (LLMs), such as non-faithful or toxic outputs, by proposing a library of compact detector models as an alternative to direct safety constraints, with ongoing efforts to deploy them for uses like guardrails and AI governance.
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 classification models that provide labels for various harms. In addition to the detectors themselves, we discuss a wide range of uses for these detector models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent challenges in their development and discuss future work aimed at making the detectors more reliable and broadening their scope.