paper-with-me

홈 › Papers

Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model

2026-04-23 · Runheng Liu, Heyan Huang, Xingchen Xiao, Zhijing Wu arxiv

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their ability to generate human-like text has raised concerns about potential misuse. This underscores the need for reliable and effective methods to detect LLM-generated text. In this paper, we propose IRM, a novel zero-shot approach that leverages Implicit Reward Models for LLM-generated text detection. Such implicit reward models can be derived from publicly available instruction-tuned and base models. Previous reward-based method relies on preference construction and task-specific fine-tuning. In comparison, IRM requires neither preference collection nor additional training. We evaluate IRM on the DetectRL benchmark and demonstrate that IRM can achieve superior detection performance, outperforms existing zero-shot and supervised methods in LLM-generated text detection.

📄 PDF Abstract BibTeX arXiv:2604.21223

Code (0)

등록된 구현이 없습니다.

Tasks

Text Detection

Similar Papers 제목 키워드 기반

Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images

2025-04-21 · Jonathan Brokman, Amit Giloni, Omer Hofman, Roman Vainshtein 외

Distinguishing between real and AI-generated images, commonly referred to as 'image detection', presents a timely and significant challenge. Despite extensive research in the (semi-)supervised regime, zero-shot and few-s…

Mixture-of-Experts

Short-PHD: Detecting Short LLM-generated Text with Topological Data Analysis After Off-topic Content Insertion

2025-04-01 · Dongjun Wei, Minjia Mao, Xiao Fang, Michael Chau

The malicious usage of large language models (LLMs) has motivated the detection of LLM-generated texts. Previous work in topological data analysis shows that the persistent homology dimension (PHD) of text embeddings can…

LLM-generated Text DetectionText DetectionTopological Data Analysis

The Impact of Prompts on Zero-Shot Detection of AI-Generated Text

2024-03-29 · Kaito Taguchi, Yujie Gu, Kouichi Sakurai

In recent years, there have been significant advancements in the development of Large Language Models (LLMs). While their practical applications are now widespread, their potential for misuse, such as generating fake new…

Text Generation

Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore

2024-05-07 · Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang 외

The efficacy of an large language model (LLM) generated text detector depends substantially on the availability of sizable training data. White-box zero-shot detectors, which require no such data, are nonetheless limited…

Language ModelingLanguage ModellingLarge Language ModelLLM-generated Text Detection+1

Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations

2024-06-27 · Ritam Dutt, Zhen Wu, Kelly Shi, Divyanshu Sheth 외

We present a generalizable classification approach that leverages Large Language Models (LLMs) to facilitate the detection of implicitly encoded social meaning in conversations. We design a multi-faceted prompt to extrac…

Dialogue Understandingdomain classification