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 9 of 14

401. ICML 2025B-score: Detecting biases in large language models using response history
402. ICML 2025CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
403. ICML 2025Certified Unlearning for Neural Networks
404. ICML 2025Circumventing Backdoor Space via Weight Symmetry
405. ICML 2025Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
406. ICML 2025Correlated Errors in Large Language Models
407. ICML 2025Detecting Strategic Deception with Linear Probes
408. ICML 2025DIS-CO: Discovering Copyrighted Content in VLMs Training Data
409. ICML 2025Discovering Spoofing Attempts on Language Model Watermarks
410. ICML 2025Disparate Conditional Prediction in Multiclass Classifiers
411. ICML 2025Do Not Mimic My Voice : Speaker Identity Unlearning for Zero-Shot Text-to-Speech
412. ICML 2025Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
413. ICML 2025ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
414. ICML 2025Embedding Safety into RL: A New Take on Trust Region Methods
415. ICML 2025Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection
416. ICML 2025EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
417. ICML 2025Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
418. ICML 2025Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations
419. ICML 2025ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
420. ICML 2025Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts
421. ICML 2025Fair Clustering via Alignment
422. ICML 2025FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation
423. ICML 2025Fast Estimation of Partial Dependence Functions using Trees
424. ICML 2025Flow Matching for Denoised Social Recommendation
425. ICML 2025From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
426. ICML 2025Gandalf the Red: Adaptive Security for LLMs
427. ICML 2025GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
428. ICML 2025Graph Inverse Style Transfer for Counterfactual Explainability
429. ICML 2025How Do Transformers Learn Variable Binding in Symbolic Programs?
430. ICML 2025Improving LLM Safety Alignment with Dual-Objective Optimization
431. ICML 2025Improving Out-of-Distribution Detection via Dynamic Covariance Calibration
432. ICML 2025Improving Out-of-Distribution Detection with Markov Logic Networks
433. ICML 2025Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning
434. ICML 2025InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
435. ICML 2025Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
436. ICML 2025Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
437. ICML 2025Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
438. ICML 2025Learning Classifiers That Induce Markets
439. ICML 2025Learning Safety Constraints for Large Language Models
440. ICML 2025Learning to Route LLMs with Confidence Tokens
441. ICML 2025Leveraging Predictive Equivalence in Decision Trees
442. ICML 2025LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning
443. ICML 2025LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
444. ICML 2025MIB: A Mechanistic Interpretability Benchmark
445. ICML 2025Mind the Gap: A Practical Attack on GGUF Quantization
446. ICML 2025Minimalist Concept Erasure in Generative Models
447. ICML 2025Mixture of Experts Made Intrinsically Interpretable
448. ICML 2025MP-Nav: Enhancing Data Poisoning Attacks against Multimodal Learning
449. ICML 2025MTL-UE: Learning to Learn Nothing for Multi-Task Learning
450. ICML 2025Near-Optimal Decision Trees in a SPLIT Second

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.