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

277 papers, page 6 of 6

251. NeurIPS 2025Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
252. NeurIPS 2025World Models Should Prioritize the Unification of Physical and Social Dynamics
253. NeurIPS 2024Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction
254. NeurIPS 2024Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
255. NeurIPS 2024Can Simple Averaging Defeat Modern Watermarks?
256. NeurIPS 2024Computational Aspects of Bayesian Persuasion under Approximate Best Response
257. NeurIPS 2024Confidence Calibration of Classifiers with Many Classes
258. NeurIPS 2024Conformalized Multiple Testing after Data-dependent Selection
259. NeurIPS 2024Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
260. NeurIPS 2024DarkSAM: Fooling Segment Anything Model to Segment Nothing
261. NeurIPS 2024Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
262. NeurIPS 2024Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
263. NeurIPS 2024Large Language Model Unlearning via Embedding-Corrupted Prompts
264. NeurIPS 2024Learning Social Welfare Functions
265. NeurIPS 2024Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
266. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
267. NeurIPS 2024Motif-oriented influence maximization for viral marketing in large-scale social networks
268. NeurIPS 2024Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
269. NeurIPS 2024Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety
270. NeurIPS 2024RedCode: Multi-dimensional Safety Benchmark for Code Agents
271. NeurIPS 2024Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
272. NeurIPS 2024Safety through feedback in Constrained RL
273. NeurIPS 2024Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
274. NeurIPS 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vector
275. NeurIPS 2024Using Noise to Infer Aspects of Simplicity Without Learning
276. NeurIPS 2023Strategyproof Voting under Correlated Beliefs
277. NeurIPS 2023Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization

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.