LLMberjack: Guided Trimming of Debate Trees for Multi-Party Conversation Creation

TL;DR

LLMberjack is a platform that transforms debate reply trees into coherent multi-party conversations, using visualization and optional LLM assistance to improve quality and reduce effort.

Contribution

It introduces an interactive tool for converting debate trees into dialogue sequences with integrated LLM support, enhancing workflow transparency and reproducibility.

Findings

Tree visualization aids in creating coherent conversation threads.

LLM assistance improves output quality and reduces human effort.

Open-source platform promotes transparent workflows.

Abstract

We present LLMberjack, a platform for creating multi-party conversations starting from existing debates, originally structured as reply trees. The system offers an interactive interface that visualizes discussion trees and enables users to construct coherent linearized dialogue sequences while preserving participant identity and discourse relations. It integrates optional large language model (LLM) assistance to support automatic editing of the messages and speakers' descriptions. We demonstrate the platform's utility by showing how tree visualization facilitates the creation of coherent, meaningful conversation threads and how LLM support enhances output quality while reducing human effort. The tool is open-source and designed to promote transparent and reproducible workflows to create multi-party conversations, addressing a lack of resources of this type.