---
title: "LEX-EC：面向黑盒场景下零样本大语言模型个性分类的词汇证据通道审计框架"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.24435v1"
permalink: "https://feed.astralor.com/items/itm_47a9ccb7f48421d571fb42a2"
published: "2026-07-27T13:45:12.000Z"
score: 70
channel: "tech"
tags: ["LEX-EC","个性分类","大语言模型","词汇消融","黑盒可解释性"]
---

# LEX-EC：面向黑盒场景下零样本大语言模型个性分类的词汇证据通道审计框架

## AI 点评

> 这篇论文针对LLM个性分类的黑盒可解释性问题提供了新颖的审计框架，值得关注的是它揭示了不同文本类型对模型关联信号的显著影响，对于从事模型可解释性和公平性研究的人员尤其有参考价值。

## 速览

论文提出LEX-EC审计框架，用于在黑盒设置下评估零样本大语言模型个性分类的可解释性。该框架结合流行度与一致性诊断及受控词汇消融，区分边际分布效应与特征关联信号。实验显示不同类型文本中信号强弱差异明显：自由散文信号最丰富但仍薄弱，研究生自我介绍中外向性关联在屏蔽后减弱，单条Facebook状态几乎无稳定证据。屏蔽主题与人口统计内容削弱部分关联，但功能词、情感词和认知风格词汇仍可检测。该框架验证了词汇方法在个性标注黑盒可解释性中的新应用。

## 关键点

- 提出LEX-EC黑盒审计框架，结合流行度、一致性诊断与受控词汇消融。
- 区分边际分布效应与特征关联信号，揭示不同文本类型中个性关联信号差异。
- 屏蔽主题和人口统计内容后，功能词、情感词和认知风格词汇仍可检测到部分关联。
- 验证词汇方法在黑盒可解释性中的新应用，提升模型透明度。

## 全文

Large language models may easily assign personality labels from text, but model interpretability remains an open problem. To address this gap, we introduce LEX-EC, a reusable black-box audit framework combining prevalence and agreement diagnostics with controlled lexical ablation to distinguish marginal-distribution effects from trait-associated signal recoverable under restricted evidence. Using this framework, we illustrate how various text genres may exhibit sharply different profiles: free-form essay text contains the broadest, but still weak, signal; in graduate student introductions, an observable Extraversion association weakened after masking; and single Facebook statuses yield little stable evidence even in a trait-balanced sample, indicating a possible lower bound of content or length. Masking topical and demographic content weakened some associations while leaving others detectable from function words, affective terms, and cognitive-style vocabulary. Linguistic prompting shifted model self-explanations but did not eliminate topical content. LEX-EC jointly evaluates classification prevalence, item-level association, chance-corrected agreement, persistence under lexical restriction, and prompt sensitivity in model-generated explanations. Across datasets, models, and prompts, LEX-EC characterizes how trait associations may vary with available lexical evidence, introducing a novel application of lexical methods to black-box interpretability in personality labeling.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_47a9ccb7f48421d571fb42a2