Saved in:
Bibliographic Details
Main Authors: Kogan, David, Nguyen, Sam, Suzuki, Masanori, Chen, Feiyang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.03317
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910040008425472
author Kogan, David
Nguyen, Sam
Suzuki, Masanori
Chen, Feiyang
author_facet Kogan, David
Nguyen, Sam
Suzuki, Masanori
Chen, Feiyang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03317
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Retcon -- a Prompt-Based Technique for Precise Control of LLMs in Conversations
Kogan, David
Nguyen, Sam
Suzuki, Masanori
Chen, Feiyang
Computation and Language
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.
title Retcon -- a Prompt-Based Technique for Precise Control of LLMs in Conversations
topic Computation and Language
url https://arxiv.org/abs/2603.03317