Diego Garcia-Olano, Yasumasa Onoe, et al.
ACL-IJCNLP 2021
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.
Diego Garcia-Olano, Yasumasa Onoe, et al.
ACL-IJCNLP 2021
Elliot Nelson, Debarun Bhattacharjya, et al.
UAI 2022
Tim Draws, Karthikeyan Natesan Ramamurthy, et al.
CHIIR 2023
Djallel Bouneffouf, Srinivasan Parthasarathy, et al.
IJCAI 2019