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

130 papers, page 2 of 3

51. ICML 2025Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning
52. ICML 2025InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
53. ICML 2025Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
54. ICML 2025Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
55. ICML 2025Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
56. ICML 2025Learning Classifiers That Induce Markets
57. ICML 2025Learning Safety Constraints for Large Language Models
58. ICML 2025Learning to Route LLMs with Confidence Tokens
59. ICML 2025Leveraging Predictive Equivalence in Decision Trees
60. ICML 2025LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning
61. ICML 2025LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
62. ICML 2025MIB: A Mechanistic Interpretability Benchmark
63. ICML 2025Mind the Gap: A Practical Attack on GGUF Quantization
64. ICML 2025Minimalist Concept Erasure in Generative Models
65. ICML 2025Mixture of Experts Made Intrinsically Interpretable
66. ICML 2025MP-Nav: Enhancing Data Poisoning Attacks against Multimodal Learning
67. ICML 2025MTL-UE: Learning to Learn Nothing for Multi-Task Learning
68. ICML 2025Near-Optimal Decision Trees in a SPLIT Second
69. ICML 2025Not All Wrong is Bad: Using Adversarial Examples for Unlearning
70. ICML 2025On Explaining Equivariant Graph Networks via Improved Relevance Propagation
71. ICML 2025On the Impact of Performative Risk Minimization for Binary Random Variables
72. ICML 2025On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
73. ICML 2025Optimizing Adaptive Attacks against Watermarks for Language Models
74. ICML 2025OR-Bench: An Over-Refusal Benchmark for Large Language Models
75. ICML 2025PASS: Private Attributes Protection with Stochastic Data Substitution
76. ICML 2025Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study
77. ICML 2025POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
78. ICML 2025Position: AI Safety Must Embrace an Antifragile Perspective
79. ICML 2025Position: AI Safety should prioritize the Future of Work
80. ICML 2025Position: Editing Large Language Models Poses Serious Safety Risks
81. ICML 2025Position: Generative AI Regulation Can Learn from Social Media Regulation
82. ICML 2025Position: Humanity Faces Existential Risk from Gradual Disempowerment
83. ICML 2025Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It
84. ICML 2025Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States
85. ICML 2025Position: The Right to AI
86. ICML 2025Position: We Need Responsible, Application-Driven (RAD) AI Research
87. ICML 2025Prediction via Shapley Value Regression
88. ICML 2025Preference learning made easy: Everything should be understood through win rate
89. ICML 2025Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
90. ICML 2025Ranked from Within: Ranking Large Multimodal Models Without Labels
91. ICML 2025Relative Error Fair Clustering in the Weak-Strong Oracle Model
92. ICML 2025Representative Ranking for Deliberation in the Public Sphere
93. ICML 2025Rethinking the Temperature for Federated Heterogeneous Distillation
94. ICML 2025SafeArena: Evaluating the Safety of Autonomous Web Agents
95. ICML 2025Safety Alignment Can Be Not Superficial With Explicit Safety Signals
96. ICML 2025Safety Reasoning with Guidelines
97. ICML 2025SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
98. ICML 2025Scaling Trends in Language Model Robustness
99. ICML 2025Selective Preference Aggregation
100. ICML 2025SEMU: Singular Value Decomposition for Efficient Machine Unlearning

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.