# The Perplexity Trap: When Patent Law Makes Human Writing Look Like AI

arXiv: https://arxiv.org/abs/2607.13044 · HTML: https://mlsanity.com/paper/2607.13044/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023)
- [Human heuristics for AI-generated language are flawed](https://mlsanity.com/paper/2206.07271/) (2022)
- [People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text](https://mlsanity.com/paper/2501.15654/) (2025)
- [DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains](https://mlsanity.com/paper/2506.06705/) (2025)
- [Detecting the Machine: A Comprehensive Benchmark of AI-Generated Text Detectors Across Architectures, Domains, and Adversarial Conditions](https://mlsanity.com/paper/2603.17522/) (2026)
- [Spotlights and Blindspots: Evaluating Machine-Generated Text Detection](https://mlsanity.com/paper/2604.16607/) (2026)

## Built on by (most cited first, 1 of 1)

- [When Words Predict Workload](https://mlsanity.com/paper/2607.04951/) (2026)

## Abstract (arXiv)

The European Patent Office (EPO) reported record filings in 2025, and the 2026 EPO Guidelines hold applicants strictly responsible for LLM-assisted content under Article 83 and Rule 42, creating pressure to triage suspected AI-generated patent text. Two constraints make this hard. First, realistic prosecution settings often have only consumer GPUs with about 8 GB VRAM, not datacenter-class scoring stacks. Second, Article 84 of the European Patent Convention requires claims to be clear and concise, pushing human drafting onto the same low-perplexity, low-burstiness manifold that LLMs occupy. We benchmark three open-source zero-shot detectors on 500 granted EPO H04 telecom patents versus 500 LLM-generated counterparts using five prompting strategies, all under the consumer hardware envelope. At claim level, all detectors exceed 60 percent false-positive rate: Binoculars 78.3 percent, Fast-DetectGPT 61.3 percent, DetectGPT 80.5 percent. The failure persists under Qwen2.5-3B-Instruct regeneration, LoRA-adapted Pythia-2.8B scoring heads, cross-IPC replication on A61K, C07D, and F03D (mean FPR 84.6 percent), and H100 re-evaluation with published Falcon-7B and GPT-J-6B heads, arguing the issue is structural rather than substitute-model capacity. A seven-feature linguistic-complexity logistic regression reaches 74.0 percent accuracy at 28.1 percent FPR, a 13 percentage-point gain over a perplexity-only baseline at a comparable operating point, without using likelihood at inference and within the same hardware budget.