Research
CreativityNeuro steers LLM weights to break mode collapse
Scaling creativity-specific weights, CreativityNeuro improves LLM divergent thinking by up to 14 percentile points and reduces mode collapse without fine-tuning.
#creativity
3 stories tagged creativity.
AI
LLM groupthink now has a novelty benchmark problem
Models tend to converge on similar answers. In Springboards tests, Flint scored 7.47 distinct replies out of 10 against LLM groupthink.
AI
How to make an LLM escape its own prior with geometry
Novel Search Space breaks an LLM out of its prior by ranking 80,000 dictionary words by embedding distance, banning the obvious neighbours, and forcing the model to brainstorm only from a surprising-but-related band.