大模型
arxiv.org ·
Once a Response, Always a Response：通过潜在提示恢复检测 LLM 生成文本
该 arXiv 论文提出免训练检测器 EchoPrompt，基于“机器生成文本依赖上游提示”的直觉：在待检文本前拼接统一通用前缀以恢复助手回复语境，用指令微调模型测量由此产生的似然增益，并以对应基座模型校准，将差值聚合为量化潜在提示依赖的分数。作者称其在零样本检测器中取得 SOTA 并保持较强鲁棒性，但摘要未披露具体数据集与指标。
AI推荐理由 arXiv 论文（v2，2026-09-26 修订），提出免训练检测器 EchoPrompt：通过前置统一通用前缀恢复“助手回复”上下文，用指令微调模型测似然增益并以基座模型校准，聚合为潜在提示依赖分数，用于零样本检测 LLM 生成文本。摘要称在零样本检测器中达到 SOTA 并具鲁棒性，但未给出具体数据集、指标数值或对比基线，效果需看全文验证；属方法层面新信息，对 AI 内容治理与检测方向有参考价值。
72
正文
Computer Science > Computation and Language
arXiv:2608.05741 (cs)
[Submitted on 6 Aug 2026 (v1), last revised 26 Sep 2026 (this version, v2)]
Title:Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration
Authors:Hongrui Bao, Yubing Ren, Jinhan You, Fang Fang, Shi Wang, Yanan Cao
View a PDF of the paper titled Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration, by Hongrui Bao and 5 other authors
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) can generate fluent and convincing text at scale, creating growing risks for misinformation dissemination, educational misuse, and platform governance. These concerns make robust detection of machine-generated text increasingly necessary. Recent zero-shot detectors mainly exploit probability-based statistical discrepancies, but they do not explicitly account for the training process of LLMs, which leaves a distinct generation mechanism insufficiently modeled and limits detection robustness. To address this issue, we propose EchoPrompt, a training-free detector based on latent prompt restoration. Our key intuition is that machine-generated text is typically produced conditioned on an upstream prompt, and this hidden dependency can be partially reactivated by prepending a unified generic prefix. Specifically, EchoPrompt restores a generic assistant-response context, measures the induced likelihood gain with an instruction-tuned model, calibrates it against the corresponding base model, and aggregates the resulting differences into a score that quantifies latent prompt dependency. Extensive experiments show that EchoPrompt achieves state-of-the-art performance among zero-shot detectors while maintaining strong robustness across challenging evaluation settings.
Comments:
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2608.05741 [cs.CL]
(or
arXiv:2608.05741v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.05741
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Hongrui Bao [view email]
[v1]
Thu, 6 Aug 2026 08:22:19 UTC (386 KB)
[v2]
Sat, 26 Sep 2026 13:43:08 UTC (334 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration, by Hongrui Bao and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2026-08
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)