# kNNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection

arXiv: https://arxiv.org/abs/2604.02008 · HTML: https://mlsanity.com/paper/2604.02008/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 78 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 4 of 4)

- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Models](https://mlsanity.com/paper/2302.10879/) (2023)
- [PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning](https://mlsanity.com/paper/2506.15683/) (2025)
- [FeatDistill: A Feature Distillation Enhanced Multi-Expert Ensemble Framework for Robust AI-generated Image Detection](https://mlsanity.com/paper/2603.21939/) (2026)

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

- [Robust Detection of LLM-Generated Text under Contamination](https://mlsanity.com/paper/2609.29935/) (2026)

## Abstract (arXiv)

LLM-generated text (LGT) detection is essential for reliable forensic analysis and for mitigating LLM misuse. Existing LGT detectors can generally be categorized into two broad classes: learning-based approaches and zero-shot methods. Compared with learning-based detectors, zero-shot methods are particularly promising because they eliminate the need to train task-specific classifiers. However, the reliability of zero-shot methods fundamentally relies on the assumption that an off-the-shelf proxy LLM is well aligned with the often unknown source LLM, a premise that rarely holds in real-world black-box scenarios. To address this discrepancy, existing proxy alignment methods typically rely on supervised fine-tuning of the proxy or repeated interactions with commercial APIs, thereby increasing deployment costs, exposing detectors to silent API changes, and limiting robustness under domain shift. Motivated by these limitations, we propose the k-nearest neighbor proxy (kNNProxy), a training-free and query-efficient proxy alignment framework that repurposes the kNN language model (kNN-LM) retrieval mechanism as a domain adapter for a fixed proxy LLM. Specifically, a lightweight datastore is constructed once from a target-reflective LGT corpus, either via fixed-budget querying or from existing datasets. During inference, nearest-neighbor evidence induces a token-level predictive distribution that is interpolated with the proxy output, yielding an aligned prediction without proxy fine-tuning or per-token API outputs. To improve robustness under domain shift, we extend kNNProxy into a mixture of proxies (MoP) that routes each input to a domain-specific datastore for domain-consistent retrieval. Extensive experiments demonstrate strong detection performance of our method.