Cover Image

$k$NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wong, Kahim, Li, Kemou, Wu, Haiwei, Zhou, Jiantao
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font Knowledge
by: Wong, Kahim, et al.
Published: (2025)

ADCD-Net: Robust Document Image Forgery Localization via Adaptive DCT Feature and Hierarchical Content Disentanglement
by: Wong, Kahim, et al.
Published: (2025)

Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore
by: Wu, Junchao, et al.
Published: (2024)

DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
by: Li, Fengpeng, et al.
Published: (2024)

LLM Unlearning with LLM Beliefs
by: Li, Kemou, et al.
Published: (2025)

Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
by: Bao, Guangsheng, et al.
Published: (2024)

Lowest Span Confidence: A Zero-Shot Metric for Efficient and Black-Box Hallucination Detection in LLMs
by: Qiao, Yitong, et al.
Published: (2026)

Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness
by: Ma, Shixuan, et al.
Published: (2024)

Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model
by: Liu, Runheng, et al.
Published: (2026)

VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text
by: Nguyen, Trieu Hai, et al.
Published: (2025)

Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling
by: Shi, Yuhui, et al.
Published: (2024)

DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains
by: Chen, Zhihui, et al.
Published: (2025)

Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
by: Bao, Guangsheng, et al.
Published: (2023)

Language Complexity Measurement as a Noisy Zero-Shot Proxy for Evaluating LLM Performance
by: Moell, Birger, et al.
Published: (2025)

VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment
by: Han, Bing, et al.
Published: (2024)

SpecDetect: Simple, Fast, and Training-Free Detection of LLM-Generated Text via Spectral Analysis
by: Luo, Haitong, et al.
Published: (2025)

M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection
by: Wang, Yuxia, et al.
Published: (2024)

Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
by: Gong, Linyuan, et al.
Published: (2023)

Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM
by: Tan, Chenkun, et al.
Published: (2025)

CrossTune: Black-Box Few-Shot Classification with Label Enhancement
by: Luo, Danqing, et al.
Published: (2024)

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
by: Hans, Abhimanyu, et al.
Published: (2024)

Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
by: Zhu, Yu, et al.
Published: (2024)

PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech
by: Wong, Michel, et al.
Published: (2025)

Toxicity Detection for Free
by: Hu, Zhanhao, et al.
Published: (2024)

Zero-Shot Detection of LLM-Generated Code via Approximated Task Conditioning
by: Ashkenazi, Maor, et al.
Published: (2025)

M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection
by: Wang, Yuxia, et al.
Published: (2023)

AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
by: Zhong, Jinzuomu, et al.
Published: (2024)

Training Deliberative Monitors for Black-Box Scheming Detection
by: Sinha, Aditya, et al.
Published: (2026)

Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator
by: Lee, Hyunji, et al.
Published: (2025)

Generalizable Synthetic Image Detection via Language-guided Contrastive Learning
by: Wu, Haiwei, et al.
Published: (2023)

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
by: Wu, Junchao, et al.
Published: (2024)

DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection
by: Wu, Junchao, et al.
Published: (2026)

PAL: Proxy-Guided Black-Box Attack on Large Language Models
by: Sitawarin, Chawin, et al.
Published: (2024)

Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction
by: Zhu, Xiaowei, et al.
Published: (2025)

Data Alignment for Zero-Shot Concept Generation in Dermatology AI
by: Gadgil, Soham, et al.
Published: (2024)

An Evaluation of Explanation Methods for Black-Box Detectors of Machine-Generated Text
by: Schoenegger, Loris, et al.
Published: (2024)

A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
by: Wu, Junchao, et al.
Published: (2023)

LPZero: Language Model Zero-cost Proxy Search from Zero
by: Dong, Peijie, et al.
Published: (2024)

SemEval-2024 Task 8: Weighted Layer Averaging RoBERTa for Black-Box Machine-Generated Text Detection
by: Datta, Ayan, et al.
Published: (2024)

Robust Detection of LLM-Generated Text: A Comparative Analysis
by: Su, Yongye, et al.
Published: (2024)