Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models

TL;DR

This paper presents PICEPR, a novel psychology-informed prompting algorithm for decoder-only LLMs that significantly improves personality recognition accuracy by 5-15%, combining content summarization and generation for better feature extraction.

Contribution

Introduction of PICEPR, a modular prompting algorithm leveraging psychology-informed content and embeddings for enhanced personality recognition with decoder-only models.

Findings

PICEPR achieves 5-15% state-of-the-art improvement in personality recognition.

Comparison of open-source and closed-source models shows content quality differences.

PICEPR effectively combines content summarization and generation for personality analysis.

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities across various natural language processing tasks. This research introduces a novel "Prompting-in-a-Series" algorithm, termed PICEPR (Psychology-Informed Contents Embeddings for Personality Recognition), featuring two pipelines: (a) Contents and (b) Embeddings. The approach demonstrates how a modularised decoder-only LLM can summarize or generate content, which can aid in classifying or enhancing personality recognition functions as a personality feature extractor and a generator for personality-rich content. We conducted various experiments to provide evidence to justify the rationale behind the PICEPR algorithm. Meanwhile, we also explored closed-source models such as \textit{gpt4o} from OpenAI and \textit{gemini} from Google, along with open-source models like \textit{mistral} from Mistral AI, to compare the quality of the generated content. The PICEPR algorithm has achieved a new state-of-the-art performance for personality recognition by 5-15\% improvement. The work repository and models' weight can be found at https://research.jingjietan.com/?q=PICEPR.