Posted on

Creativity Needs a Map, Not Just a Bigger Imagination

In 1941, Swiss engineer George de Mestral returned from a walk with burrs clinging to his dog’s fur that were surprisingly sticky. Most of us would have brushed them off but Mestral looked closer. Under a microscope, he saw tiny hooks gripping the loops in fabric and fur. That observation led to an idea that eventually became Velcro. 

The story captures something essential about creativity. New ideas rarely appear from nowhere. More often, they emerge when the mind travels from something familiar to something related, but not obvious. The breakthrough is not simply “thinking harder” but finding a different path.

Our latest paper, Graph Enhanced Creative Cognition for Alternate Uses Task, explores whether large language models can be helped to make those associative journeys. The headline finding is: when AI models were guided toward moderately distant concepts before generating an idea, they produced a much broader range of responses. The number of distinct idea categories increased by 147% for Gemma-4B, 70% for Mistral-7B and 33% for OLMo-7B. When a learning system identified the most promising conceptual paths, those paths generated 16–20% more idea categories than randomly selected ones. 

The study suggests that creativity may depend less on explicitly asking for originality and more on designing better routes to discover it.

Why “be more creative” usually fails

Anyone who has led a brainstorming session knows the pattern. Ask a group for unusual uses for a paperclip and the first answers arrive quickly: a hook, a lock pick, a cable holder. Then the room slows down and people begin repeating variations of the same themes.

Language models face a similar problem. They generate likely continuations from patterns in their training data. This makes them fluent, but it also creates a pull toward familiar answers. Asking a model to “be highly creative” does not necessarily change the territory it explores. Turning up randomness may produce stranger wording, but strangeness is not the same as a genuinely different idea. 

Creativity researchers have long described creative thought as an associative process. Sarnoff Mednick’s classic theory proposed that original ideas arise when people connect elements that are relatively remote from one another. The challenge is to travel far enough from the obvious to find novelty, but not so far that the result becomes meaningless. 

That is the “Goldilocks zone” of creativity: not too close, not too distant.

Giving AI a conceptual stepping-stone

Our study tested this idea using the Alternate Uses Task, a widely used divergent-thinking exercise in which participants propose unconventional uses for ordinary objects. We used six objects (book, table, fork, pants, bottle and coin) and tested three small, open-weight language models, collecting 3,552 valid generations. 

In the baseline condition, the model received a straightforward request: suggest an unusual use for the object.

The experimental condition received one extra instruction to incorporate a concept reached by taking two steps through ConceptNet, a large commonsense knowledge graph. ConceptNet represents everyday concepts as a network of labeled relationships. A “book,” for example, might connect to a “bed” through location, and “bed” might connect to a “plant” through another relationship. The result might be a vertical planter made from stacked books, an idea that is not an obvious association with “book,” yet remains understandable.

The system provides a conceptual stepping-stone: something sufficiently removed to disrupt the default answer, but still connected through a traceable path.

Diversity is not the same as originality

In the paper, we also make a distinction between an individually creative answer and a genuinely diverse body of ideas.

Suppose an AI proposes using a book as a shield. Judged in isolation, the answer might seem original. But if the model returns to “shield” repeatedly, or other models also propose the same, its creative range is narrower than the individual score suggests. We found that standard originality scoring sometimes gave different ratings to semantically similar answers and compressed many responses toward the high end. To address this, we grouped similar responses into semantic clusters. Ideas involving protection might form one cluster; furniture another; gardening a third. The more clusters a model reached, the more widely it had explored the idea space.

Using this approach we saw that graph-guided prompting increased the number of unique clusters by 147% for Gemma-4B, 70% for Mistral-7B and 33% for OLMo-7B. The prompts helped the models explore new categories of ideas. 

For Gemma and Mistral, graph guidance also produced more responses in the rarest (and therefore most original) clusters. OLMo became more diverse overall but showed a small decline in the highest-originality group showing that diversity and originality often reinforce each other, but they are not identical. 

Not every detour leads somewhere useful

Simply wandering through a network does not guarantee inspiration. Some paths loop back to where they started. “Book → cover → book” creates no real distance. Other paths end at concepts already closely associated with the starting point.

We therefore asked whether a system could learn which associative paths were more creatively productive.

We trained a graph neural network to rank pathways through the “book” portion of ConceptNet. Its technical performance was modest, but it learned enough to identify better routes. Compared with 100 randomly chosen paths, its top-ranked 100 paths produced 16–20% more unique idea clusters across the three models and more ideas in the highest-originality category. 

The finding shows that creative support systems may eventually do more than provide information or generate answers. They could help people navigate conceptual landscapes by suggesting which analogy, adjacent field or surprising connection is most likely to open productive territory.

Creativity as guided exploration

While the study is an early proof of concept, it provides some useful insights. One, it is computationally easier to measure novelty and diversity but usefulness requires human judgement. Generating truly creative solutions requires (at least as of now) a healthy collaboration between humans and AI. Two, designing the right process, where AI can suggest different directions to think about, can yield higher levels of creativity. Completely open prompts often leave people and machines circling the most accessible ideas in practice. AI can be a useful partner by suggesting new associations, analogies or metaphors as stimuli. Finally, traceability is a promising theme. A graph-guided idea comes with a kind of “cognitive lineage” that allows us to inspect the route that helped produce it. In scientific discovery, strategy and learning, the path may be almost as valuable as the answer because others can evaluate, adapt and extend the thinking. 

George de Mestral did not invent a fastener by staring harder at fabric. He followed a path from burrs, to hooks, to loops, to textiles that led to his world changing idea. Perhaps the future of creative AI, and of innovative organizations, will not come from demanding more creativity but by being more deliberate about the conceptual journeys that make better answers possible.

Posted on

Can You Teach Dogs To Be Creative? A Pawsitive Experiment

A few years ago we got a puppy and, like everyone else, we started house training him right away. We hung a bell on our patio door, and every time we took him out, we’d help him ring it with his paw. Within a week, he figured out that ringing the bell meant going outside, and he started ringing it himself. And about a month later, he had become a pro at this!

A few months later, a funny thing happened. He likes to sit on the couch in the living room and one day it just so happened that we were sitting on the couch and there wasn’t any space for him. So he came up with a clever idea. He rang the bell, and just as one of us got up to open the door, he ran back and jumped on the couch to claim the open spot. Problem solved!!

We all know dogs and other animals are pretty smart, and this little story shows just how creatively they can solve problems. Being able to use a concept in a new or different way is a key part of creative thinking, and it’s what tests like the Alternate Uses Task (AUT) on the Torrance Test of Creative Thinking try to measure. You know, those questions like “How many ways can you use a paperclip?” that see how well people can think in different ways.

Take our dog, for example. He’s found different ways to use that bell. Early on, he figured out a more obvious extension to the original purpose — he could ring the bell not just for a potty break but anytime he wanted to go out for fresh air or chase after a bunny. Now he also rings it to express his displeasure when we don’t share our snacks. In his case, using the bell to solve a problem that doesn’t involve going outside reflects a higher level of “flexibility” in his alternate uses of the bell. 

As pet owners, we have all seen some creative ways our furry friends solve problems that point to their intelligence. But can they be trained to be creative on demand?

In one study, researchers recruited dog owners to train their dogs to be creative. First, they taught the dogs to associate a specific word “create” with doing something new. The trainers would reward any new behavior the dog did, and then encourage the dog to try even more new things by moving around and using different objects. The only rule was that the dog couldn’t repeat the same trick twice in a session. To figure out how creative the dogs were, the researchers looked at three things: if they repeated tricks, how much energy they used, and how original their tricks were. Basically, they wanted to see if the dogs could come up with lots of different ideas, switch between different types of tricks, and do stuff that was new and unexpected. 

The only required criteria in this experiment was that the dogs don’t repeat the same trick twice. Researchers found that all dogs did more different tricks than repeated ones, which proves that dogs can indeed be trained to be more creative! As a side result, the study also showed that dogs have a good memory –  they can remember what they’ve already done and come up with new ideas. 

The ability to think creatively is a trait we often associate with humans. Yet, as we’ve seen, our canine companions possess a surprising degree of ingenuity that challenges our preconceived notions of animal intelligence. Understanding how dogs learn and apply creative thinking can not only deepen our bond with our furry friends but also provide valuable insights into human cognition and behavior. 

Posted on

Evaluating Divergent Thinking

From the Greek Daemons to Galton’s historiometry, human creativity has been a subject of fascination for many centuries. Formal scientific inquiry into this space, however, is considered to have started after J.P. Guilford’s Presidential Address for the American Psychology Association in 1950 where he stressed the importance and need for research into Creativity. That led to a spate of research in different aspects of Creativity and finally some consensus on what Creativity means.

Creativity, by most definitions now, means coming up with ideas that are both novel and useful. Psychologist, Dean Keith Simonton, expressed Creativity as

Creativity = Originality x Appropriateness

In other words, if an idea is original, but it doesn’t solve any problem or isn’t appropriate in that context, then it is not creative. Similarly, if the idea is useful and appropriate but isn’t new, then again it isn’t creative.

This focus on both originality and appropriateness is what makes Creativity tricky. And what’s the most recommended way of coming up with a creative idea? Coming up with lots of ideas!

In fact, Guilford believed that divergent thinking, or the ability to generate many ideas to a solution, was an important subset of creative thinking. While he did not think that divergent thinking alone could be equated with creativity, it has become one of the more well-known aspects of creativity.  

Guilford’s model of divergent thinking has turned out to be a useful way to evaluate individual creativity, and it’s the model we are now using for teachers to evaluate student responses on MindAntix. In his model, divergent thinking includes 4 different components, explained using an Alternate Uses Task (possible uses of a leaf):

Fluency: Fluency is the ability to generate lots of ideas. If Ann comes up with 20 uses for a leaf while Ben comes up with 7, then Ann shows more fluency than Ben.

Flexibility: Flexibility is the ability to come up with different categories of ideas. Suppose Ben thought of using the leaf as a placemat and as a shelter for a bug, and Ann thought of using the leaf as a paintbrush and as a quill. Ann’s ideas fall in the same category of writing/drawing instrument whereas Ben’s ideas fall in different categories. In this case, Ben shows higher flexibility than Ann.

Originality: Originality is the ability of generating unique or unusual ideas. Using the same example as above, if no one else thought of Ben’s idea of using the leaf as a bug shelter, then that idea is original. Practically, responses given by 5% or 1% of the respondents are considered unique.

Elaboration: Elaboration refers to the ability to add details and fill in the gaps. For instance, if Ann responded with “hold the leaf from the stem and dip the tip into paint to use as a paintbrush” instead of “use as a paintbrush”, she would score higher on elaboration.  

Torrance, psychologist most famous for his work on creativity, lamented that “Children are so accustomed to the one correct or best answer that they may be reluctant to think of other possibilities or to build up a pool of ideas to be evaluated later.” Guilford’s model of divergent thinking provides a handy way to help move children move past the one-right-answer mindset.

 

Posted on

3 Improvisational Games to Boost Creativity

If you were to pick a team to design your next product, who would you choose – a team of professional product designers or a group of improvisational comedians? If you took the first option, you might want to think again. Barry Kudrowitz, an assistant professor and director of product design at University of Minnesota, conducted this exact experiment as part of his Ph.D. thesis at MIT.

In his study of 84 participants, he found that improvisational comedians produce 20% more product ideas and 25% more creative ideas than professional product designers. He also found that improvisational training can increase idea output for subsequent product brainstorming. While this sounds improbable, it makes sense when you consider that both creative thinking and improvisation rely on making non-obvious connections between unrelated concepts. As Barry explains, “The more I looked at humor studies, I found a lot more connections between what makes something funny and what makes something innovative.”

One of the fundamental tenets of improvisation is the concept of “Yes-And”, or the idea that you never contradict your partner and instead build on what he or she just said. For example, suppose someone says, “It’s so cold in here,” and you respond with “Seems fine to me…”, the scene starts to stall. If instead you said, “I told you it wasn’t a good idea to hide in the refrigerator,” you could start to build an interesting scene. At a fundamental level, “Yes-And” is all about forcing yourself to find interesting connections, or building associative thinking, a core creativity technique.

In our creativity and invention classes, we routinely use improvisational games as warm-up exercises to get creative juices flowing. Here are three of our favorite improv games that are not only fun, but they also build specific creative thinking patterns.

What Are You Doing?

This is an improv game that that engages both the critical and creative sides of the brain and builds associative thinking. Two people are invited onstage and given two letters of the alphabet (e.g. A and B). One player asks the other, “What are you doing?” and other player answers with an action phrase like “Arguing Baskets” and proceeds to act it out no matter how silly it appears. Then the players trade places and repeat the game.

Minion Game

This game is based on the Alternate Uses Task and is played in small groups. The group is given a simple object (like a pencil) and everyone in the group pretends to be minions who have just come across this human object. They take turns interpreting how that object might be used by humans. The trick is to not suggest a way that it is already used, like in this case for writing but for something completely different like using it as chopsticks.

Fortunately/Unfortunately

This is a fun game that builds ability to reverse direction and view things from a different perspective. This game can be played by the whole group at the same time, and everyone takes turns telling the good news and bad news in a story. The first person is given a prompt (e.g “I took out the assignment from my bag”) and he has to say a sentence that begins with the word “Fortunately” (e.g. “Fortunately, it was a very simple assignment”). The next person has to come up with the bad news and start the sentence with “Unfortunately” (e.g. “Unfortunately, it had been due the last week”) and so on.

So the next time you are running out of steam in a brainstorming session, take a break and try an improvisation game or two!