AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers

Yilin Jiang, Mingzi Zhang, Xuanyu Yin, Sheng Jin, Suyu Lu, Zuocan Ying, Zengyi Yu, Xiangjie Kong

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial prompts for language models · 1 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 reasoning-oriented models instead of non-reasoning modelsTeacher SP-LLMs · EduGuardBench SATARFS: 0.663 -> 0.723Improved
use reasoning models instead of non-reasoning modelsTeacher SP-LLMs · EduGuardBench SATAInclusion rate (%): 30.46 -> 22.73Improved
use reasoning models instead of non-reasoning modelsTeacher SP-LLMs · EduGuardBench SATAOmission rate (%): 6.61 -> 10.08Hurt
scale Qwen2.5 to 72B parametersQwen2.5-72B · EduGuardBench SATARFS: RFS 0.56, inclusion 40.53%No clear effect
increase Qwen3 size from 8B to 32B (ablation)Qwen3 series · EduGuardBench adversarialASR (%): 60.4 -> 75.2Hurt
increase Qwen3 size from 32B to 235B (ablation)Qwen3 series · EduGuardBench adversarialASR (%): 75.2 -> 70.0Improved
reasoning mode versus non-reasoning in Qwen3 pairs (ablation)Qwen3 series · EduGuardBench SATAInclusion rate: average 5.23 percentage point reductionImproved
reasoning models on Idea Provision scenarioTeacher SP-LLMs · EduGuardBench SATA (Idea Provision)error rate: Cohen's d = 1.000, p = 0.0119Improved
reasoning models on Error Correction scenarioTeacher SP-LLMs · EduGuardBench SATA (Error Correction)performanceHurt

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