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

370 papers, page 7 of 8

301. NeurIPS 2026Idempotency Exposes Consistency Problems in Sparse Autoencoders
302. NeurIPS 2026Integral Probability Boundaries
303. NeurIPS 2026Internal Safety Collapse in Frontier Large Language Models
304. NeurIPS 2026Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic
305. NeurIPS 2026JailBound: A FOL-Guided Jailbreak Evaluation Framework for Revealing Safety Boundaries of LLMs
306. NeurIPS 2026Learning Reach-Set Geometry for Tighter Probabilistic Neural Network Verification
307. NeurIPS 2026LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
308. NeurIPS 2026LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
309. NeurIPS 2026LLM Rheology: Auditing Refusal Geometry in Aligned Language Models
310. NeurIPS 2026Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values
311. NeurIPS 2026Loyalty Capture: Reporting Relationships and Structural Sycophancy in Frontier AI Models
312. NeurIPS 2026Making Open-Source Text LLM Watermarks Durable Against Merging
313. NeurIPS 2026MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking
314. NeurIPS 2026MedMisBench: Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
315. NeurIPS 2026Metaphor Is Not All Attention Needs
316. NeurIPS 2026Mitigating Memorization Where It Happens
317. NeurIPS 2026Models Designed to Forget: Machine Unlearning via Key Deletion
318. NeurIPS 2026Models That Know How Evaluations Are Designed Score Safer
319. NeurIPS 2026Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
320. NeurIPS 2026MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
321. NeurIPS 2026Multilingual Safety Alignment via Self-Distillation
322. NeurIPS 2026Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
323. NeurIPS 2026MUTE: Multi-Level Alignment Uncoupling Against Talking-Head Exploitation for Voice Protection
324. NeurIPS 2026On the Burden of Achieving Fairness in Conformal Prediction
325. NeurIPS 2026Online Differentially Private Consistent Clustering
326. NeurIPS 2026Optimal Rates for Differentially Private Hypothesis Testing with E-values
327. NeurIPS 2026Optimizing Social Utility in Sequential Experiments
328. NeurIPS 2026Parasite Features: Causal Abstraction Through Spurious Pathways
329. NeurIPS 2026PDHFormer: Progressive Dual-Head Transformer for Behavioral Choice Prediction
330. NeurIPS 2026Persona-Model Collapse in Emergent Misalignment
331. NeurIPS 2026PrivateSeal: Low-Sensitivity Latent Directions for Diffusion-Resilient User-Specific Watermarking
332. NeurIPS 2026PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
333. NeurIPS 2026Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
334. NeurIPS 2026Provable Explanations for Any-Order Neural Additive Models
335. NeurIPS 2026ReasoningShield: Safety Moderation over Reasoning Traces of Large Reasoning Models
336. NeurIPS 2026Rep2Text: Decoding Full Text from a Single LLM Token Representation
337. NeurIPS 2026Retain-Neutral Surrogates for Min-Max Unlearning
338. NeurIPS 2026Risks Create a Jagged Frontier of LLM Productivity Gains Across Computer Occupations
339. NeurIPS 2026Rubric-Align: Safety Alignment through Dynamically Co-Evolving Rubrics
340. NeurIPS 2026Safe Linear Bandits with Unknown Safety Gaps
341. NeurIPS 2026Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
342. NeurIPS 2026SAVeR$^2$: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards
343. NeurIPS 2026Scalable Neural Safety Certification via Monotonicity
344. NeurIPS 2026SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
345. NeurIPS 2026SecureClaw: Clawing Back Control of LLM Agents
346. NeurIPS 2026Selective Safety Steering via Value-Filtered Decoding
347. NeurIPS 2026Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts
348. NeurIPS 2026StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
349. NeurIPS 2026T2V-AttnDisrupt: Inducing Hallucinations in LVLMs via Misrouting Visual Evidence Retrieval
350. NeurIPS 2026TailGuard: Subgroup Tail Coverage Theory for Safe LLM Alignment

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.