Kombine benchmark: LLMs out-combine average humans, but struggle at concept blending
windx0303 · x · 2026-10-14
A multi-institution team (UChicago, Princeton, Stony Brook, UIUC and more) introduces Kombine, a benchmark for LLM combinatorial creativity — combining familiar ideas in unfamiliar ways, central to scientific breakthroughs.
Key findings:
- LLMs are more combinatorially creative than the average human
- Conceptual blending is the hardest task; even frontier models struggle
- LLMs tend to homogenize, inventing concepts with the same properties across separate models
- Humans and LLMs combine ideas in distinct regions of semantic space
- The authors anticipate greater conceptual diversity via human-AI collaboration
More from Research
- RFD4-Proteina's 'underrated' docs detail partial diffusion for protein redesign — AllThingsApx · 2026-10-23
- MPI-Sec PhD Thesis on Vulnerability Detection Benchmarks Includes Pre-LLM Classic "Top Score on the Wrong Exam" — mboehme_ · 2026-10-23
- LiveNerf's 29-day data finds no nerfing of Claude Opus 5.5 — TheOnlyVibemaster · 2026-10-23
- New paper makes 9 falsifiable predictions toward a major AI-enabled terror attack by 2027-2028 — StephenLCasper · 2026-10-23
- HumanoidPose recovers humanoid robots' full-body joint states from RGB video alone — cholz · 2026-10-23
- Sophont's Holon-S1 predicts genes and biomarkers from routine pathology slides — iScienceLuvr · 2026-10-23