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

arXiv: https://arxiv.org/abs/2604.21223 · HTML: https://mlsanity.com/paper/2604.21223/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 32 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [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)
- [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)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [RADAR: Robust AI-Text Detection via Adversarial Learning](https://mlsanity.com/paper/2307.03838/) (2023)
- [Free Process Rewards without Process Labels](https://mlsanity.com/paper/2412.01981/) (2024)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs](https://mlsanity.com/paper/2406.10216/) (2024)
- [DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text](https://mlsanity.com/paper/2305.17359/) (2023)
- [Unifying Human and Statistical Evaluation for Natural Language Generation](https://mlsanity.com/paper/1904.02792/) (2019)
- [Real or Fake? Learning to Discriminate Machine from Human Generated Text](https://mlsanity.com/paper/1906.03351/) (2019)
- [Ghostbuster: Detecting Text Ghostwritten by Large Language Models](https://mlsanity.com/paper/2305.15047/) (2023)
- [Raidar: geneRative AI Detection viA Rewriting](https://mlsanity.com/paper/2401.12970/) (2024)
- [DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios](https://mlsanity.com/paper/2410.23746/) (2024)
- [Training-free LLM-generated Text Detection by Mining Token Probability Sequences](https://mlsanity.com/paper/2410.06072/) (2024)
- [Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood](https://mlsanity.com/paper/2406.19874/) (2024)
- [Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection](https://mlsanity.com/paper/2412.11506/) (2024)
- [Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness](https://mlsanity.com/paper/2409.16914/) (2024)
- [ReMoDetect: Reward Models Recognize Aligned LLM's Generations](https://mlsanity.com/paper/2405.17382/) (2024)
- [DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains](https://mlsanity.com/paper/2506.06705/) (2025)

## Built on by (most cited first, 4 of 4)

- [DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities](https://mlsanity.com/paper/2606.04205/) (2026)
- [Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration](https://mlsanity.com/paper/2608.05741/) (2026)
- [Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts](https://mlsanity.com/paper/2605.12890/) (2026)
- [Who's Behind the Text? Robust Model Authorship Attribution](https://mlsanity.com/paper/2610.19583/) (2026)

## Abstract (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.