From job titles to jawlines: Using context voids to study generative AI systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917990535004160 |
|---|---|
| author | Memon, Shahan Ali De, Soham Kang, Sungha Mujtaba, Riyan AlShebli, Bedoor Davis, Katie Snyder, Jaime West, Jevin D. |
| author_facet | Memon, Shahan Ali De, Soham Kang, Sungha Mujtaba, Riyan AlShebli, Bedoor Davis, Katie Snyder, Jaime West, Jevin D. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From job titles to jawlines: Using context voids to study generative AI systems Memon, Shahan Ali De, Soham Kang, Sungha Mujtaba, Riyan AlShebli, Bedoor Davis, Katie Snyder, Jaime West, Jevin D. Computers and Society Artificial Intelligence Human-Computer Interaction 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. |
| title | From job titles to jawlines: Using context voids to study generative AI systems |
| topic | Computers and Society Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2504.13947 |