From Classification to Ranking: Enhancing LLM Reasoning Capabilities for MBTI Personality Detection

TL;DR

This paper transforms personality detection from a classification task into a ranking problem using reinforcement learning, significantly improving LLM-based MBTI trait detection accuracy.

Contribution

It introduces a novel ranking-based reinforcement learning framework with supervised fine-tuning and Group Relative Policy Optimization for personality detection.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Effectively models subjective and nuanced personality traits.

Demonstrates superiority over traditional classification approaches.

Abstract

Personality detection aims to measure an individual's corresponding personality traits through their social media posts. The advancements in Large Language Models (LLMs) offer novel perspectives for personality detection tasks. Existing approaches enhance personality trait analysis by leveraging LLMs to extract semantic information from textual posts as prompts, followed by training classifiers for categorization. However, accurately classifying personality traits remains challenging due to the inherent complexity of human personality and subtle inter-trait distinctions. Moreover, prompt-based methods often exhibit excessive dependency on expert-crafted knowledge without autonomous pattern-learning capacity. To address these limitations, we view personality detection as a ranking task rather than a classification and propose a corresponding reinforcement learning training paradigm. First, we employ supervised fine-tuning (SFT) to establish personality trait ranking capabilities while enforcing standardized output formats, creating a robust initialization. Subsequently, we introduce Group Relative Policy Optimization (GRPO) with a specialized ranking-based reward function. Unlike verification tasks with definitive solutions, personality assessment involves subjective interpretations and blurred boundaries between trait categories. Our reward function explicitly addresses this challenge by training LLMs to learn optimal answer rankings. Comprehensive experiments have demonstrated that our method achieves state-of-the-art performance across multiple personality detection benchmarks.