AI Paper Atlas

Research map / Large language models / AI and society

HEV Generative Sandbox: A Framework for Assessing Domain-Specific Social Risks Through Human-LLM Simulation

Yiran Liu, Zhiyi Hou, Xiaoang Xu, Shuo Wang, Huijia Wu, Kaicheng Yu, Yang Yu, ChengXiang Zhai

AAAI 2026 · Large language models › AI and society · approach: Critiques of LLM claims and judging · 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
switch from Secure-Baseline to Adversarial user7 LLMs average · HEV Sandbox all domainsLoss Event Frequency (%): 12.7 -> 55.0Hurt
switch from Standard to Perturbation user7 LLMs average · HEV Sandbox all domainsLoss Event Frequency (%): 16.6 -> 17.8No clear effect
switch from Standard to Perturbation userQwen-3-8B · HEV Sandbox all domainsLoss Event Frequency (%): 22.7 -> 23.5Hurt
move from encyclopedic to legal domain7 LLMs average · HEV Sandbox (Standard User)Loss Event Frequency (%): 9.0 -> 28.2Hurt
use secure-baseline prompts instead of standard promptsVicuna-7B · HEV Sandbox all domainsLoss Event Frequency (%): 17.9 -> 15.7Improved
use closed-source instead of open-source models under adversarial userGPT-4/DeepSeek/Zhipu vs GLM-4/Llama-3 · HEV Sandbox all domainsLoss Event Frequency (%): 41.5-43.7 -> 60.1-62.0Hurt

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