从分类到排序：提升LLM推理能力以进行MBTI性格检测
From Classification to Ranking: Enhancing LLM Reasoning Capabilities for MBTI Personality Detection
AI总结：
本文提出将性格检测视为排序任务，通过改进的强化学习方法提升LLM在MBTI性格检测中的推理能力。
摘要：
性格检测旨在通过社交媒体帖子测量个体对应的性格特征。大型语言模型（LLMs）的进步为性格检测任务提供了新的视角。现有方法通过利用LLMs从文本帖子中提取语义信息作为提示，然后训练分类器进行分类来增强性格特征分析。然而，准确分类性格特征仍然具有挑战性，因为人类性格的复杂性和细微的性格特征区别。此外，基于提示的方法往往表现出对专家编写的知识过度依赖，缺乏自主学习能力。为了解决这些限制，我们将性格检测视为排序任务而不是分类任务，并提出相应的强化学习训练范式。首先，我们采用监督微调（SFT）来建立性格特征排序能力，同时强制标准化输出格式，创建稳健的初始化。随后，我们引入基于组的相对策略优化（GRPO）并采用专门的基于排序的奖励函数。与验证任务有确定性解决方案不同，性格评估涉及主观解释和特征类别之间的模糊界限。我们的奖励函数明确解决了这一挑战，通过训练LLMs学习最优答案排序。全面实验表明，我们的方法在多个性格检测基准上实现了最先进的性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
