arXiv：cs.AI· Kibum Moon, Dan R. Johnson, Kostadin Kushlev, Benjamin Lira, Indre Viskontas, James C. Kaufman, Roger E. Beaty, Angela L. Duckworth, Adam E. Green·· 6 小时前
研究：AI 语义盲区中的人类想法并不逊色
Thinking Outside the Bots: Human Ideas in AI's Semantic Blind Spots Are Not Inferior
AI 导读
研究团队开发 EDGE 方法，在大学申请文书、物品替代用途和人际建议三类开放式任务中对比人类与 AI 生成的想法，发现人类回答延伸至 AI 输出覆盖稀疏的语义区域，且这些独特人类想法在创造力、质量和有效性上并无明显劣势，部分结果评分与成就反而更优。研究还发现，越独特的人类想法往往获得越高的创造力评分，而这一关系在 AI 想法中较弱甚至相反。
正文
Abstract:AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas. Does the human heterogeneity that extends beyond AI reflect valuable thinking that AI misses? Alternatively, is greater human heterogeneity driven by lower-quality ideas and less effective thinking that AI avoids? We developed Expansion of Divergent Generative Expression (EDGE) to map AI's semantic "blind spots" by assessing how strongly/weakly individual human ideas were represented in a task-matched AI semantic comparison set. Specifically, we compared human-generated vs. AI-generated ideas across three open-ended tasks: college admissions essays, alternative uses for everyday objects, and interpersonal advice. Across all three tasks, human responses extended into semantic regions sparsely covered by AI outputs. These distinctively human responses showed no meaningful deficits in creativity, quality, or effectiveness, were associated with equal-or-better academic performance, and with credibly superior ratings and achievement for some outcomes. These ideas were thus not merely poor-performing variation; they performed as well as or better than ideas that overlapped more strongly with AI ideas. More distinctive human ideas tended to receive higher creativity ratings, but this relationship was weak or reversed for AI ideas. Taken together, these results suggest that differentiation among human-generated ideas does not reflect poor thinking that AI can safely omit, and instead may afford both individual and population-level advantages.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.17324 [cs.CL] |
| (or arXiv:2610.17324v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17324 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kibum Moon [view email]
[v1]
Mon, 12 Oct 2026 19:31:44 UTC (7,397 KB)
来源：arXiv：cs.AI · arxiv.org