# The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices

arXiv: https://arxiv.org/abs/2603.18482 · HTML: https://mlsanity.com/paper/2603.18482/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 77 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 30 of 40)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)](https://mlsanity.com/paper/2510.22954/) (2025)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [Truncation Sampling as Language Model Desmoothing](https://mlsanity.com/paper/2210.15191/) (2022)
- [Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?](https://mlsanity.com/paper/2212.12131/) (2022)
- [Locally Typical Sampling](https://mlsanity.com/paper/2202.00666/) (2022)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [Testing the Predictions of Surprisal Theory in 11 Languages](https://mlsanity.com/paper/2307.03667/) (2023)

## Built on by (most cited first, 3 of 3)

- [Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding](https://mlsanity.com/paper/2606.22511/) (2026)
- [Reference-Based Analysis of Coherence and Diversity in Open-Ended Text Generation](https://mlsanity.com/paper/2609.28080/) (2026)
- [Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem](https://mlsanity.com/paper/2610.15570/) (2026)

## Abstract (arXiv)

Why does machine-generated text remain detectable? We investigate a mechanistic explanation at the decoding stage: standard strategies such as top-k and nucleus sampling restrict generation to high-probability tokens, while human writers routinely choose contextually appropriate words from deeper in the model's probability distribution. Truncation makes a measurable share of these choices unreachable; we call this the truncation blind spot. Across five open models and three domains, 8--18% of human-selected tokens fall outside common truncation boundaries. Linguistic analysis further reveals disproportionate exclusion of content-word tokens. In a benchmark comprising 1.8 million machine generations, classifiers using only predictability and lexical diversity achieve mean AUC-ROC near 0.97, with substantial variation across decoding settings and strong transfer across generators. Probability-floor samplers substantially narrow the blind spot, demonstrating that the choice of truncation criterion matters for retaining human-used tokens. Together, these findings characterize a source of human--machine distributional mismatch and motivate decoding methods that preserve contextually appropriate low-probability choices while maintaining generation quality. Code and data are available at https://github.com/EstebanGarces/humanvsmachine.