AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

D&R: Recovery-based AI-Generated Text Detection via a Single Black-box LLM Call

Yuxia Sun, Ran Zhang, Aoxiang Sun, Xu Li, Zitao Liu, Jingcai Guo

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Zero-shot machine-text detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add D&R single-call recovery detection instead of RAIDAR multi-call rewritingRAIDAR · Long-text datasets avgAUROC: 0.8770 -> 0.9602Improved
use D&R instead of RAIDAR on short textsRAIDAR · Short-text datasetsAUROC: 0.7248 -> 0.8687Improved
use Within-Chunk Shuffling instead of Global Shuffling (ablation)D&R · Long-text avgAUROC: 0.5564 -> 0.9602Improved
use Within-Chunk Shuffling instead of Chunk-Order Shuffling (ablation)D&R · Long-text avgAUROC: 0.7423 -> 0.9602Improved
add semantic similarity (BERTScore F1) to the classifier features (ablation)D&R · Long-text avg, 4 advanced source modelsAUROC: 0.6906 -> 0.9614Improved
add structural similarity (Kendall tau, Spearman rho) to the classifier features (ablation)D&R · Long-text avg, 4 advanced source modelsAUROC: 0.7707 -> 0.9614Improved
use a small local recovery model (Mistral-7B) instead of DeepSeek-v3 (ablation)D&R · Long-text, 4 advanced source modelsAUROC: 0.9614 -> 0.9359Hurt
use a different source model than the recovery model (ablation)D&R · Long-text avgAUROC: 0.9793 -> 0.9603Hurt
use a different source model than the recovery model (ablation)RAIDAR · Long-text avgAUROC: 0.9712 -> 0.8792Hurt
apply paraphrase attack to AI text (ablation)D&R · RAID benchmarkAUROC: 0.8736 -> 0.8210Hurt
replace multi-call RAIDAR by single-call D&R for efficiencyRAIDAR · per-sample latencyseconds: 15 -> 2Improved
increase recovery-model temperature from 0.2 to 0.8 (ablation)D&R recovery similarity · ML-ArXiv-Papersrecovery similarityHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy