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 1 of 6

1. NeurIPS 2026A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
2. NeurIPS 2026Agent MechSuits : Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents
3. NeurIPS 2026Agentic-imodels: Evolving agentic interpretability tools via autoresearch
4. NeurIPS 2026AI-Mediated Communication Can Steer Collective Opinion
5. NeurIPS 2026Amortized Linear-time Exact Shapley Value for Product-Kernel Methods
6. NeurIPS 2026Are Well-Trained Surrogates Optimal? Rethinking the Surrogate Role with Instability for Unlearnable Examples
7. NeurIPS 2026Attack Selection In Agentic AI Control Evaluations Meaningfully Decreases Safety
8. NeurIPS 2026Auditor-Assisted Summary-Channel Verification for Hosted LLM Identity Substitution
9. NeurIPS 2026BarrierSteer: LLM Safety via Learning Barrier Steering
10. NeurIPS 2026Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
11. NeurIPS 2026Beyond Feature Disruption: Boundary-Diverting Unlearnable Examples against Linear Probing
12. NeurIPS 2026Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs
13. NeurIPS 2026Black-Box Inference of LLM Architectural Properties with Restrictive API Access
14. NeurIPS 2026BSO: Safety Alignment Is Density Ratio Matching
15. NeurIPS 2026CalArena: A Large Scale Post-Hoc Calibration Benchmark
16. NeurIPS 2026CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
17. NeurIPS 2026Can VLMs Reason When to Stop for Human Safety?
18. NeurIPS 2026Castle-in-the-Air: Probing the Foundational Visual Deficits of MLLMs via Bottom-Up Cognitive Factors
19. NeurIPS 2026Chatter Attack: Resource Consumption Attack for Large Language Models
20. NeurIPS 2026Cognitive bias benchmarks should incorporate insights from ecological rationality
21. NeurIPS 2026Community-Centered AI is Feasible and Beneficial for Impacted Communities
22. NeurIPS 2026Compact Representations of Impact-Based Fair-Ranking Policies
23. NeurIPS 2026Compressing Collections of Trees with Decision Equivalence
24. NeurIPS 2026Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction--Concealment Tradeoff in MLLMs
25. NeurIPS 2026DACE: Diversity-Driven Adversarial Co-Evolution for Robust LLM Safety Alignment
26. NeurIPS 2026Decentralized AI Governance Must Decouple Policy Processing from Capability Enforcement
27. NeurIPS 2026Decomposing One Professional-Framing Pipeline: Which Components Shift LLM Safety Boundaries?
28. NeurIPS 2026Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
29. NeurIPS 2026DIAL: A Bounded-Monotone Adapter with Closed-Form Residual $L_\infty$ Bounds for Scalar-Controlled Refusal Modulation
30. NeurIPS 2026Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
31. NeurIPS 2026Distributionally Robust Algorithmic Recourse for Tree Ensembles
32. NeurIPS 2026Do Thinking Tokens Help with Safety?
33. NeurIPS 2026Dual-Contrastive Sparse Autoencoders Reveal Features of Musical Interpretation
34. NeurIPS 2026Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
35. NeurIPS 2026Embeddings for Preferences, Not Semantics
36. NeurIPS 2026Escape the Context Manifold: Preventing DiT In-Context Editing via Conditional Flow Hijacking
37. NeurIPS 2026Evaluation Awareness in Language Models Has Limited Effect on Behaviour
38. NeurIPS 2026Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
39. NeurIPS 2026Finding Interpretable Prompt-Specific Circuits in Language Models
40. NeurIPS 2026Fine-tuning Does Not Reach All: Uneven Safety and Knowledge Dynamics in Language Models
41. NeurIPS 2026From Post-Hoc to Ante-Hoc: Consistently Explainable Semi-Supervised Time Series Classification
42. NeurIPS 2026From Tokens to Tactics: Adversarial Text Optimization in an Axis-Aligned Rhetorical Strategy Space for Harmful Content Detection
43. NeurIPS 2026GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization
44. NeurIPS 2026Gradient-based Graph Structure Optimisation for Research Networks
45. NeurIPS 2026Gradient-Mine Units: Scorched-Earth Strategy for Model Protection against Unauthorized Fine-Tuning
46. NeurIPS 2026GradShield: Alignment Preserving Finetuning
47. NeurIPS 2026Harnessing Textual Refusal Directions for Multimodal Safety
48. NeurIPS 2026Hierarchical Conformal Classification
49. NeurIPS 2026How Do Agentic LLMs Decide to Call Tools? A Scaffold Default Controlled by Suppression
50. NeurIPS 2026How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness

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.