Large Language Model Programs
This approach improves LLM capabilities for tasks like question-answering, but it is incremental as it builds on existing in-context learning methods.
The paper tackles the problem of enhancing large language models (LLMs) by embedding them within algorithms or programs, resulting in a 6.4% improvement over chain-of-thought baselines for evidence-supported question-answering without fine-tuning.
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 parameterise 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 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.