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

688 papers, page 8 of 14

351. NeurIPS 2026Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
352. NeurIPS 2026Tcell: Mitigating Harmful Fine-tuning for Large Language Models via Gradient Alignment
353. NeurIPS 2026Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
354. NeurIPS 2026TensorCommitments: A Lightweight Verifiable Inference for Large Language Models
355. NeurIPS 2026The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network
356. NeurIPS 2026The Alignment Tax Concentrates in Output Projections
357. NeurIPS 2026The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
358. NeurIPS 2026The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
359. NeurIPS 2026The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
360. NeurIPS 2026Tight PAC-Bayes Generalisation Guarantees for Large Language Model Safety Monitoring
361. NeurIPS 2026Towards Fair Graph Generation Without Sensitive Attribute
362. NeurIPS 2026Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
363. NeurIPS 2026Training ML Models with Predictable Failures
364. NeurIPS 2026TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation
365. NeurIPS 2026Unsupervised Unlearnable Segmentation via Semantic Structure Disruption
366. NeurIPS 2026Untrusted Content Masking for Web Agents with Security Guarantees
367. NeurIPS 2026UpSafe℃: Upcycling for Controllable Safety in Large Language Models
368. NeurIPS 2026Values Are Not Single Labels: Distributional Value Profiling Across Groups and Contexts
369. NeurIPS 2026When Poison Meets Structure: Topology-based Defense against Poisoning Attack on Graph-based Retrieval-Augmented Generation
370. NeurIPS 2026Where Should Society Draw the Line? A Social Choice Approach to Collective Consent
371. CVPR 2025Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
372. ICLR 2025A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
373. ICLR 2025Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
374. ICLR 2025Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
375. ICLR 2025Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
376. ICLR 2025Durable Quantization Conditioned Misalignment Attack on Large Language Models
377. ICLR 2025Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
378. ICLR 2025On the Role of Attention Heads in Large Language Model Safety
379. ICLR 2025Programming Refusal with Conditional Activation Steering
380. ICLR 2025Safety Alignment Should be Made More Than Just a Few Tokens Deep
381. ICLR 2025Safety Layers in Aligned Large Language Models: The Key to LLM Security
382. ICLR 2025The Hidden Cost of Waiting for Accurate Predictions
383. ICML 2025(How) Can Transformers Predict Pseudo-Random Numbers?
384. ICML 2025$S^2$FGL: Spatial Spectral Federated Graph Learning
385. ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
386. ICML 2025A Lens into Interpretable Transformer Mistakes via Semantic Dependency
387. ICML 2025A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
388. ICML 2025A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
389. ICML 2025Activation Space Interventions Can Be Transferred Between Large Language Models
390. ICML 2025Adversarial Reasoning at Jailbreaking Time
391. ICML 2025Adversaries Can Misuse Combinations of Safe Models
392. ICML 2025Algorithmic Recourse for Long-Term Improvement
393. ICML 2025An Efficient Private GPT Never Autoregressively Decodes
394. ICML 2025An End-to-End Model for Logits-Based Large Language Models Watermarking
395. ICML 2025Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
396. ICML 2025Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
397. ICML 2025Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
398. ICML 2025Automatically Interpreting Millions of Features in Large Language Models
399. ICML 2025Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
400. ICML 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

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.