Beyond the Name: Demographic Leakage in De-Identified Résumés and Evaluation Artifacts in LLM Bias Audits

2026-09-14

AI Summary

研究探讨了简历去标识化后仍存在的种族文化推断问题，通过控制语言属性一致来测试非语言文本的影响，并发现显著性是评估模型偏差的关键因素。

Abstract

De-identified résumé screening assumes that redacting explicit fields prevents ethnocultural inference; however, recent audits attribute residual leakage to declared languages. We investigate whether eliminating language fields resolves this leakage across nine open-weight models and 620 counterfactual résumés. By holding language attributes strictly identical, we isolate unstructured prose across five ethnocultural conditions and three cue-salience tiers. Target-group recovery averages 0.757 overall and saturates at 1.000 under high salience, demonstrating that non-language prose sustains demographic inference. Crucially, models diverge only under faint cues (0.086-0.690), establishing salience as an essential evaluation axis. Furthermore, pairwise LLM-as-a-judge outcomes are highly sensitive to evaluation design: forbidding ties yields an apparent selection-rate ratio of 0.39 alongside strong position and content effects, whereas permitting ties produces near-universal ties for most models ($\ge94\%$). Downstream scoring shows only very small between-condition differences, highlighting the need to distinguish demographic signals recoverable from résumé content from effects introduced by the evaluation protocol.

Problem

• demographic leakage
• de-identified rsums
• ethnocultural inference
• salience
• LLM bias

Innovation

• demographic inference
• non-language prose
• cue salience
• evaluation design sensitivity
• resume content