用简历生成头像，暴露AI在缺失信息下的偏见。
From job titles to jawlines: Using context voids to study generative AI systems
- 通过简历生成头像，制造信息空白来探测AI行为。
- 模型在缺乏身体特征时生成带有偏见的视觉形象。
- 适合关注AI伦理与偏见的研究者和开发者。
本文提出一种探索生成式AI系统行为的推测性设计方法，将设计作为研究手段。通过连接看似无关的领域，构建有意的信息空白（context void），以特定任务为探针，考察AI模型在极端不确定性下的表现。我们以ChatGPT（GPT-4与DALL-E）为例，尝试从专业简历（CV）生成人物头像。该方法超越传统评估方式，在模型必须填补大量缺失信息的条件下，揭示其隐含的刻板印象与价值判断。通过对模型如何解读简历中的身份与能力线索并转化为视觉形象的定性分析，发现系统在信息空白中会生成带有偏见的表征，可能依赖刻板联想或明显幻觉。
原文摘要 · Abstract (English)
In this paper, we introduce a speculative design methodology for studying the behavior of generative AI systems, framing design as a mode of inquiry. We propose bridging seemingly unrelated domains to generate intentional context voids, using these tasks as probes to elicit AI model behavior. We demonstrate this through a case study: probing the ChatGPT system (GPT-4 and DALL-E) to generate headshots from professional Curricula Vitae (CVs). In contrast to traditional ways, our approach assesses system behavior under conditions of radical uncertainty -- when forced to invent entire swaths of missing context -- revealing subtle stereotypes and value-laden assumptions. We qualitatively analyze how the system interprets identity and competence markers from CVs, translating them into visual portraits despite the missing context (i.e. physical descriptors). We show that within this context void, the AI system generates biased representations, potentially relying on stereotypical associations or blatant hallucinations.
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。