As AI-generated text continues to evolve, distinguishing it from human-authored content has become increasingly difficult. This study examined whether non-expert readers could reliably differentiate between AI-generated poems and those written by well-known human poets. We conducted two experiments with non-expert poetry readers and found that participants performed below chance levels in identifying AI-generated poems (46.6% accuracy, χ2(1, N = 16,340) = 75.13, p < 0.0001). Notably, participants were more likely to judge AI-generated poems as human-authored than actual human-authored poems (χ2(2, N = 16,340) = 247.04, p < 0.0001). We found that AI-generated poems were rated more favorably in qualities such as rhythm and beauty, and that this contributed to their mistaken identification as human-authored. Our findings suggest that participants employed shared yet flawed heuristics to differentiate AI from human poetry: the simplicity of AI-generated poems may be easier for non-experts to understand, leading them to prefer AI-generated poetry and misinterpret the complexity of human poems as incoherence generated by AI.
  • treefrog@lemm.eeEnglish
    2·
    1 month ago

    The patterns in poetry date back to when writing was less common. They’re mnemonic devices.

    Today, they’re still valuable when performing poetry.

    I tend to not follow typical rhyme patterns, use off rhymes, non-ending lines, alliterations, etc. instead. I always found the typical rhyme schemes I was taught in school stifling, but as I’ve practiced my craft more, I have gotten more comfortable incorporating them into my toolbox.

    Anyway, so many non-poets commenting in this thread. People who are serious about poetry know that they’re unlikely to make a living off it. We write because we get joy out of making and sharing our art. A lot of poetry is still performed at open mics and poetry slams. And most of it is shared with people we know who appreciate it. In other words, most poetry isn’t written with the intention of ever publishing it.

    It’s something we enjoy playing with, in other words. And until a machine can experience joy and playfulness, they’re not doing art. Only copying it.