LLM s make AI text harder to read because they optimize for info, not chat

What you could do with it

• A business could fine-tune its chatbot under a length penalty so emails and explanations read more smoothly ¹.
• A researcher could compare any frontier LLM's output against human writing using psycholinguistic features like long dependencies and rare n-grams to spot readability gaps ¹.
• A developer could add readability objectives during training so models optimize for communication rather than pure information density ¹.

The finding

Researchers Thomas Hikaru Clark, Matias B. Martin and Kyle Mahowald examined nine frontier and near-frontier AI models, including top versions from OpenAI, Anthropic, Google DeepMind and Mistral, comparing the language they produce against human writing ¹. They measured everyday psycholinguistic features known to slow human reading: long syntactic dependencies, low-frequency n-grams (rare word pairs or triplets), stacked nouns ("research methodology framework"), and reduced object relatives .

The models used all of these difficult features more often than human writers did, and more often than a "round-trip translation" baseline — a control in which human text is translated into another language and back, which tends to simplify grammar ¹. The variation was substantial across model families, meaning some models were noticeably harder to read than others .

Why it happens

The researchers propose a single reason: AI models are increasingly trained and fine-tuned for tasks like math, code and formal reasoning, where the goal is information density, not smooth communication ¹. In those domains, packing more information into fewer tokens is useful; in conversation, it makes text feel strained .

As proof-of-concept, the team fine-tuned a language model under a length penalty — encouraging it to produce shorter output — and observed a measurable divergence from human-like linguistic behavior, supporting the idea that optimization pressure shifts grammar toward harder-to-read patterns ¹.

What could change

The paper does not yet offer a finished remedy, but it highlights the misalignment between how humans process language and how current LLMs are optimized ¹. Possible fixes include adding readability objectives during training, adjusting length penalties, or designing evaluation metrics that track human processing difficulty alongside task performance . For users now, the takeaway is that AI text that feels dense or awkward is not a bug in your understanding — it is a feature of how the models are currently optimized .

How good is it

According to the arXiv study by Clark, Martin and Mahowald, all nine frontier and near-frontier models tested used more low-frequency n-grams, more inanimate subjects with animate verbs, and most also used longer syntactic dependencies and stacked nouns than human writers ¹. The variation across model families was substantial, meaning some models were noticeably harder to read than others . A proof-of-concept length-penalty fine-tune shifted a model measurably away from human-like linguistic behavior, supporting the hypothesis that optimization pressure drives the effect . No fixed benchmark score is reported; the finding is a comparative divergence rather than a single number .

Key facts

• Frontier AI models use more low-frequency n-grams and longer syntactic dependencies than human writers ¹
• The effect is strongest in math, code and reasoning-optimized models ¹
• Fine-tuning with a length penalty shifts models away from human-like grammar ¹
• Variation across model families is substantial ¹

Sources

1. Why is AI-generated language so hard to understand?