SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02896 · 2024

LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

While both agent interaction and personalisation are vibrant topics in research on large language models (LLMs), there has been limited focus on the effect of language interaction on the behaviour of persona-conditioned LLM agents. Such an endeavour is important to ensure that agents remain consistent to their assigned traits yet are able to engage in open, naturalistic dialogues. In our experiments, we condition GPT-3.5 on personality profiles through prompting and create a two-group population of LLM agents using a simple variability-inducing sampling algorithm. We then administer personality tests and submit the agents to a collaborative writing task, finding that different profiles exhibit different degrees of personality consistency and linguistic alignment to their conversational partners. Our study seeks to lay the groundwork for better understanding of dialogue-based interaction between LLMs and highlights the need for new approaches to crafting robust, more human-like LLM personas for interactive environments.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.02896")
get_code_for_paper("2402.02896")
have("2402.02896")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.02896.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.02896.svg)](https://syntology.ai/paper/2402.02896)

Connect an agent — have() is free.