AI Paper Atlas

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

Model-Agnostic Sentiment Distribution Stability Analysis for Robust LLM-Generated Texts Detection

Siyuan Li, Xi Lin, Guangyan Li, Zehao Liu, Aodu Wulianghai, Li Ding, Jun Wu, Jianhua Li

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Zero-shot machine-text detection · 3 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
use sentiment distribution stability (SDC) instead of best baseline detectordetector on GPT-4-0613 text · five datasets avgF1 (%): 63.62 -> 71.19Improved
use SentiDetect-SDC instead of best baselinedetector on Gemini-1.5-Pro text · five datasets avgF1 (%): 61.53 -> 71.65Improved
use SentiDetect-SDC instead of best baselinedetector on LLaMa-3.3 text · five datasets avgF1 (%): 72.37 -> 85.17Improved
use SentiDetect-SDP instead of RAIDARdetector on GPT-4-0613 text · HumanEvalF1 (%): 67.48 -> 82.74Improved
use SentiDetect instead of baselines under adversarial perturbationdetector · HumanEval perturbedF1 (%): 24.26 -> 48.05Improved
increase number of LER prompts I from 3 to 9 (ablation)SentiDetect-SDC · Student EssayF1 (%): 59.03 -> 56.60No clear effect
increase number of LER prompts I from 3 to 9 (ablation)SentiDetect-SDC · Yelp ReviewF1 (%): 77.02 -> 77.63No clear effect
use SentiDetect-SDC instead of GPT-Zerodetector on LLaMa-3.3 text · PaperF1 (%): 87.61 -> 89.22No clear effect
shorten input text to about 20 words (ablation)SentiDetect · detection lengthF1Mixed

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