Why is AI generated language so hard to understand?
Why is AI generated language so hard to understand?
Research found that text generated by AI models uses language features more frequently associated with understanding difficulty, such as long syntactic dependencies, low-frequency n-grams, and the use of inanimate subjects with active verbs, compared to human writing. Compared to human writing, 9 cutting-edge and near-cutting-edge models use more low-frequency n-grams, most of which also use longer dependencies, more stacked nouns, and more ellipsis of object clauses, with significant differences among models. The study suggests that AI text is optimized for goals such as mathematics, code, and reasoning, leading to information density prioritizing effective communication, and this hypothesis is verified by fine-tuning language models.
Abstract:There is a widespread sense that AI-generated text has recently become harder to understand. In this study, we investigate a set of psycholinguistic features that are known to correlate with human processing difficulty (e.g., object relative clauses, long syntactic dependencies, low-frequency n-grams). Using a novel corpus of AI-generated text across diverse domains, we find that AI models use these difficult features more often than paraphrases generated by round-trip translation. Compared with human writing, all nine frontier and near-frontier models use more inanimate subjects with animate verbs and more low-frequency n-grams, and most also use longer dependencies, more stacked nouns, and more reduced object relatives in conversation; we also demonstrate substantial variation across model families. We propose and test a hypothesis as to why: while human language is optimized for successful communication, AI-generated text is increasingly optimized for other goals like math, code, and reasoning, in which there is a pressure for \textit{information density} rather than successful communication. We provide a proof-of-concept for this hypothesis by fine-tuning a language model under a length penalty, which leads to a divergence from human-like linguistic behavior. Our findings highlight the axes of misalignment between linguistic processing demands in humans and LLMs, and point toward possible remedies.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29162 [cs.CL] |
| (or arXiv:2610.29162v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29162 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Thomas Clark [view email]
[v1]
Wed, 21 Oct 2026 03:54:08 UTC (528 KB)
Source: Hacker News · AI hot posts · arxiv.org