检测大模型教育咨询中的社会偏见，发现描述越具体，偏见越小。
Sociodemographic Biases in Educational Counselling by Large Language Models
- 用900个学生案例测试6个大模型，覆盖14类社会特征，生成24.3万条回应。
- 描述越模糊，偏见差距几乎翻三倍；具体信息可显著降低偏差。
- 不同模型偏见模式差异大，需个性化数据保障公平性，适合教育AI审慎设计者。
随着大型语言模型（LLMs）在教育场景中日益普及，理解其潜在偏见至关重要。本研究考察了基于LLM的教育咨询中的社会人口学偏见。我们评估了六款LLM对900个学生情景案例的回应，每个案例在14种社会人口学标识（涵盖种族、性别、经济地位、移民背景等）及对照条件下进行测试，共产生243,000条模型输出。研究发现：（1）所有模型均表现出可测量的偏见；（2）偏见模式部分与已知的人类偏见一致，但存在显著差异；（3）偏见程度受学生描述精确度强烈影响——模糊或简略的信息使偏差几乎增加三倍，而具体、个性化的细节可显著缓解偏见；（4）各模型的偏见特征差异明显。结果表明，情境丰富且个性化的学生表征至关重要，提示以人工智能驱动的教育决策应依赖详尽的学生特定信息，以促进公平与公正。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) are increasingly integrated into educational settings, understanding their potential biases is critical. This study examines sociodemographic biases in LLM-based educational counselling. We evaluate responses from six LLMs answering questions about 900 vignettes describing students in diverse circumstances. Each vignette is systematically tested across 14 sociodemographic identifiers - spanning race and gender, socioeconomic status, and immigrant background - along with a control condition, yielding 243,000 model responses. Our findings indicate that (1) all models exhibit measurable biases, (2) bias patterns partially align with documented human biases but diverge in notable ways, (3) the magnitude of these biases is strongly influenced by the precision of the student descriptions, where vague or minimal information amplifies disparities nearly threefold, while concrete, individualised metrics substantially reduce them, and (4) bias profiles vary substantially across models. These results demonstrate the importance of context-rich and personalised educational representations, suggesting that AI-driven educational decisions benefit from detailed student-specific information to promote fairness and equity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。