AI Paper Atlas

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

Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text

Hongyi Zhou, Jin Zhu, Kai Ye, Ying Yang, Erhan Xu, Chengchun Shi

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Zero-shot machine-text detection · 5 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
learn the distance function instead of fixed rewrite distances (RAIDAR)rewrite-based detector · GPT-3.5 Turbo text, 21 domainsAUC: 0.745 (RAIDAR) -> 0.948Improved
use a learned rewrite distance instead of ML logits-based ImBDImBD · GPT-3.5 Turbo text, 21 domainsAUC: 0.890 -> 0.948Improved
use L2D versus zero-shot FDGPT per domainFDGPT · Gemini 1.5 Pro text, per domainAUC: Code 0.829 -> 0.979; ArtCulture 0.982 -> 0.955Mixed
use L2D on unseen prompts (rewrite, polish, expand)ImBD · News, GPT-4oAUC: 0.943 -> 0.998Improved
use L2D on Wiki with Claude-3.5ImBD · Wiki, Claude-3.5AUC: 0.961 -> 0.950Hurt
add a learned distance (fine-tuned LM) vs fixed pre-trained model distance (FD) (ablation)L2D · same settings as unseen-prompt experimentsAUC: average improvement of 97.1%Improved
paraphrasing or decoherence attacks on LLM textL2D · News, Wiki, StoryAUCNo clear effect
compare runtime to RAIDARL2D · GPT-3.5 Turbo textruntime: slight increase over RAIDARMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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