Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations

Swapnaja Achintalwar, Ioana Baldini, Djallel Bouneffouf, Joan Byamugisha, Maria Chang, Pierre Dognin, Eitan Farchi, Ndivhuwo Makondo, Aleksandra Mojsilović, Manish Nagireddy, Karthikeyan Natesan Ramamurthy, Inkit Padhi, Orna Raz, Jesus Rios, Prasanna Sattigeri, Moninder Singh, Siphiwe A. Thwala, Rosario A. Uceda-Sosa, Kush R. Varshney

Abstract: The alignment of large language models is usually done by model providers to add or control behaviors that are common or universally understood across use cases and contexts. By contrast, in this article, we present an approach and architecture that empowers application developers to tune a model to their particular values, social norms, laws, and other regulations and orchestrate between potentially conflicting requirements in context. We lay out three main components of such an Alignment Studio architecture: Framers, Instructors, and Auditors, which work in concert to control the behavior of a language model. We illustrate this approach with a running example of aligning a company’s internal-facing enterprise chatbot to its business conduct guidelines.

External IDs:doi:10.1109/mic.2024.3453671