“Large Language Model Programs”, Imanol Schlag, Sainbayar Sukhbaatar, Asli Celikyilmaz, Wen-tau Yih, Jason Weston, Jürgen Schmidhuber, Xian Li2023-05-09 (Codex, inner monologue (AI))⁠:

In recent years, large pre-trained language models (LLMs) have demonstrated the ability to follow instructions and perform novel tasks from a few examples. The possibility to parameterize an LLM through such in-context examples widens their capability at a much lower cost than finetuning.

We extend this line of reasoning and present a method which further expands the capabilities of an LLM [OPT] by embedding it within an algorithm or program.

To demonstrate the benefits of this approach, we present an illustrative example of evidence-supported question-answering. We obtain a 6.4% improvement over the chain-of-thought baseline through a more algorithmic approach without any finetuning.

Furthermore, we highlight recent work from this perspective and discuss the advantages and disadvantages in comparison to the standard approaches.