Retcon -- a Prompt-Based Technique for Precise Control of LLMs in Conversations

TL;DR

Retcon, a few-shot prompting technique designed to provide turn-level control over LLMs in conversations, is presented and it is demonstrated that it performs significantly better than zero-shot and traditional few-shot prompting.

Abstract

Recent advances in Large Language Models (LLMs) allow agents to execute complex natural language tasks. Many LLM applications, such as support agents, teaching assistants, and interactive bots, involve multi-turn conversations. However, it remains challenging to control LLMs in the context of such interactions, particularly when the LLM behavior needs to be adjustable over the course of the conversation. In this paper, we present Retcon, a few-shot prompting technique designed to provide turn-level control over LLMs in conversations. We then demonstrate that it performs significantly better than zero-shot and traditional few-shot prompting.