Social aspects · safety papers, 2023–2026

Key findings

• Social aspects · safety went from 4 papers in 2023 to 370 in 2026, roughly 93x in three years.
• ICML publishes the most Social aspects · safety work: 364 papers from 2023 to 2026, 53% of the four-venue total.
• The fastest-growing overlap is with Alignment and Safety: papers tagged with both rose from 0 in 2023 to 137 in 2026.
• Among the 5 topics under Alignment and Responsible AI, it ranks #3 by 2026 paper count; the fastest grower in the group, Social aspects · privacy, is up 6.6x versus 93x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026BarrierSteer: LLM Safety via Learning Barrier Steering
• ICML 2026Anti-Backdoor Coreset Selection via Cumulative Entropy
• ICLR 2026Bi-Criteria Metric Distortion
• CVPR 2026Omni-MMSI Toward Identity-attributed Social Interaction Understanding
• NeurIPS 2025Safety Pretraining: Toward the Next Generation of Safe AI
• ICML 2025$S^2$FGL: Spatial Spectral Federated Graph Learning
• ICLR 2025The Hidden Cost of Waiting for Accurate Predictions
• CVPR 2025Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
• NeurIPS 2024Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety
• ICML 2024Optimally Improving Cooperative Learning in a Social Setting
• ICLR 2024The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
• CVPR 2024Digital Life Project: Autonomous 3D Characters with Social Intelligence
• NeurIPS 2023Strategyproof Voting under Correlated Beliefs
• ICML 2023Adaptive Coordination in Social Embodied Rearrangement
• NeurIPS 2026Beyond Feature Disruption: Boundary-Diverting Unlearnable Examples against Linear Probing
• ICML 2026AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
• ICLR 2026PRISON: Unmasking the Criminal Potential of Large Language Models
• CVPR 2026Spot The Ball A Benchmark for Visual Social Inference
• NeurIPS 2025SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
• ICML 2025Adversaries Can Misuse Combinations of Safe Models

All Social aspects · safety papers

364 papers, page 5 of 8

201. ICML 2026Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
202. ICML 2026Token-Efficient Change Detection in LLM APIs
203. ICML 2026Toward Calibrated Mixture-of-Experts Under Distribution Shift
204. ICML 2026Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
205. ICML 2026Towards Context-Invariant Safety Alignment for Large Language Models
206. ICML 2026Towards Functional Correctness of Large Code Models with Selective Generation
207. ICML 2026Towards Seed-Robust Safety Alignment in Text-to-Image Models
208. ICML 2026Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions
209. ICML 2026TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention
210. ICML 2026TSFAdv: Frequency-Guided Black-Box Adversarial Attacks on Time Series Forecasting
211. ICML 2026Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs
212. ICML 2026Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows
213. ICML 2026Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
214. ICML 2026Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
215. ICML 2026Weight-sparse transformers have interpretable circuits
216. ICML 2026What is Missing? Explaining Neurons Activated by Absent Concepts
217. ICML 2026When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
218. ICML 2026When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
219. ICML 2026When Random Saliency Looks Trained: Architectural Center Bias in CNN Interpretability
220. ICML 2026When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
221. ICML 2026Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
222. ICML 2026Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
223. ICML 2026Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
224. ICML 2026X-EviProbe: Post-hoc Parameter-Free Evidential Uncertainty Quantification for Frozen Graph Neural Networks
225. ICML 2026Z-Erase: Enabling Concept Erasure in Single Stream Diffusion Transformers
226. ICML 2026ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
227. ICML 2025(How) Can Transformers Predict Pseudo-Random Numbers?
228. ICML 2025$S^2$FGL: Spatial Spectral Federated Graph Learning
229. ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
230. ICML 2025A Lens into Interpretable Transformer Mistakes via Semantic Dependency
231. ICML 2025A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
232. ICML 2025A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
233. ICML 2025Activation Space Interventions Can Be Transferred Between Large Language Models
234. ICML 2025Adversarial Reasoning at Jailbreaking Time
235. ICML 2025Adversaries Can Misuse Combinations of Safe Models
236. ICML 2025Algorithmic Recourse for Long-Term Improvement
237. ICML 2025An Efficient Private GPT Never Autoregressively Decodes
238. ICML 2025An End-to-End Model for Logits-Based Large Language Models Watermarking
239. ICML 2025Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
240. ICML 2025Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
241. ICML 2025Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
242. ICML 2025Automatically Interpreting Millions of Features in Large Language Models
243. ICML 2025Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
244. ICML 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
245. ICML 2025B-score: Detecting biases in large language models using response history
246. ICML 2025CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
247. ICML 2025Certified Unlearning for Neural Networks
248. ICML 2025Circumventing Backdoor Space via Weight Symmetry
249. ICML 2025Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
250. ICML 2025Correlated Errors in Large Language Models

FAQ

How many Social aspects · safety papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

688 in total: 4 in 2023, 41 in 2024, 273 in 2025, 370 in 2026.

How many Social aspects · safety papers are at NeurIPS 2026?

NeurIPS 2026 has 121 Social aspects · safety papers, versus 131 the year before.

How many Social aspects · safety papers are at ICLR 2026?

ICLR 2026 has 20 Social aspects · safety papers, versus 11 the year before.

How many Social aspects · safety papers are at ICML 2026?

ICML 2026 has 226 Social aspects · safety papers, versus 130 the year before.

How many Social aspects · safety papers are at CVPR 2026?

CVPR 2026 has 3 Social aspects · safety papers, versus 1 the year before.

Which conference publishes the most Social aspects · safety papers?

ICML, with 364 papers from 2023 to 2026.