AI Paper Atlas

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

HLD: Approximate Hierarchical Linguistic Distribution Modeling for LLM-Generated Text Detection

Rui Guo, Weibin Zeng, Fuzhang Wu, Yan Kong, sicheng shen, Yanjun Wu, Weiming Dong

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

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 word-level features (ablation)HLD · DetectRL Review (train on Arxiv)AUROC: 84.43 -> 91.54Improved
add POS features (ablation)HLD · DetectRL Review (train on Arxiv)AUROC: 88.10 -> 91.54Improved
add dependency features (ablation)HLD · DetectRL Review (train on Arxiv)AUROC: 90.05 -> 91.54Improved
add semantic features (ablation)HLD · DetectRL Review (train on Arxiv)AUROC: 87.31 -> 91.54Improved
add semantic features (ablation)HLD · DetectRL Writing (train on Arxiv)AUROC: 76.24 -> 79.40Improved
add POS features (ablation)HLD · DetectRL Writing F1 (train on Arxiv)F1: 72.99 -> 71.90Hurt
use HLD instead of RoBERTa-baseHLD vs Roberta-base · DetectRL multi-LLM avgAUROC: 98.24 -> 99.12Improved
use HLD instead of RoBERTa-baseHLD vs Roberta-base · DetectRL cross-domain (train on Arxiv)AUROC: 81.38 -> 86.61Improved
use HLD instead of RoBERTa-baseHLD vs Roberta-base · DetectRL paraphrase attackAUROC: 73.00 -> 97.04Improved
use HLD instead of DPICHLD vs DPIC · DetectRL adversarial attacks avgAUROC: 93.03 -> 97.85Improved
increase n-gram context length k beyond 5HLD word-level · DetectRLAUROCHurt
use HLD instead of Fast-DetectGPT/RAIDAR proxy modelsHLD · inference timetotal time (s): 35.13 -> 5.24Improved

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