社会层面 · safety论文趋势 2023–2026
AI 社会议题：safety
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 688 篇被归入该主题的论文。
主要结论
- 社会层面 · safety论文从 2023 年的 4 篇增长到 2026 年的 370 篇，三年间扩大到约 93 倍。
- ICML 是发社会层面 · safety论文最多的会议，2023–2026 年共 364 篇，占四个会议总量的 53%。
- 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 137 篇。
- 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的社会层面 · privacy是 6.6 倍，社会层面 · safety是 93 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 2 | 0 | 2 | 0 | 4 |
| 2024 | 23 | 11 | 6 | 1 | 41 |
| 2025 | 131 | 11 | 130 | 1 | 273 |
| 2026 | 121 | 20 | 226 | 3 | 370 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- 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
全部社会层面 · safety论文
共 364 篇，第 7 / 8 页
- ICML 2025PASS: Private Attributes Protection with Stochastic Data Substitution
- ICML 2025Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study
- ICML 2025POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
- ICML 2025Position: AI Safety Must Embrace an Antifragile Perspective
- ICML 2025Position: AI Safety should prioritize the Future of Work
- ICML 2025Position: Editing Large Language Models Poses Serious Safety Risks
- ICML 2025Position: Generative AI Regulation Can Learn from Social Media Regulation
- ICML 2025Position: Humanity Faces Existential Risk from Gradual Disempowerment
- ICML 2025Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It
- ICML 2025Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States
- ICML 2025Position: The Right to AI
- ICML 2025Position: We Need Responsible, Application-Driven (RAD) AI Research
- ICML 2025Prediction via Shapley Value Regression
- ICML 2025Preference learning made easy: Everything should be understood through win rate
- ICML 2025Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
- ICML 2025Ranked from Within: Ranking Large Multimodal Models Without Labels
- ICML 2025Relative Error Fair Clustering in the Weak-Strong Oracle Model
- ICML 2025Representative Ranking for Deliberation in the Public Sphere
- ICML 2025Rethinking the Temperature for Federated Heterogeneous Distillation
- ICML 2025SafeArena: Evaluating the Safety of Autonomous Web Agents
- ICML 2025Safety Alignment Can Be Not Superficial With Explicit Safety Signals
- ICML 2025Safety Reasoning with Guidelines
- ICML 2025SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
- ICML 2025Scaling Trends in Language Model Robustness
- ICML 2025Selective Preference Aggregation
- ICML 2025SEMU: Singular Value Decomposition for Efficient Machine Unlearning
- ICML 2025ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
- ICML 2025Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
- ICML 2025SPRI: Aligning Large Language Models with Context-Situated Principles
- ICML 2025STAIR: Improving Safety Alignment with Introspective Reasoning
- ICML 2025Statistical Collusion by Collectives on Learning Platforms
- ICML 2025STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification
- ICML 2025Stealix: Model Stealing via Prompt Evolution
- ICML 2025Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings
- ICML 2025Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups
- ICML 2025Tensor Product Neural Networks for Functional ANOVA Model
- ICML 2025Test-Time Multimodal Backdoor Detection by Contrastive Prompting
- ICML 2025The Elicitation Game: Evaluating Capability Elicitation Techniques
- ICML 2025The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
- ICML 2025The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
- ICML 2025The Limits of Predicting Agents from Behaviour
- ICML 2025The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
- ICML 2025TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
- ICML 2025Towards Attributions of Input Variables in a Coalition
- ICML 2025Towards Black-Box Membership Inference Attack for Diffusion Models
- ICML 2025Towards flexible perception with visual memory
- ICML 2025Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models
- ICML 2025TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
- ICML 2025Trustworthy Machine Learning through Data-Specific Indistinguishability
- ICML 2025Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查社会层面 · safety在 ICML 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "social-safety"}
常见问题
- 2023–2026 年四大会议一共有多少篇社会层面 · safety论文？
- 共 688 篇，按年份分别是 2023 年 4 篇、2024 年 41 篇、2025 年 273 篇、2026 年 370 篇。
- NeurIPS 2026 有多少篇社会层面 · safety论文？
- NeurIPS 2026 有 121 篇社会层面 · safety论文，上一届是 131 篇。
- ICLR 2026 有多少篇社会层面 · safety论文？
- ICLR 2026 有 20 篇社会层面 · safety论文，上一届是 11 篇。
- ICML 2026 有多少篇社会层面 · safety论文？
- ICML 2026 有 226 篇社会层面 · safety论文，上一届是 130 篇。
- CVPR 2026 有多少篇社会层面 · safety论文？
- CVPR 2026 有 3 篇社会层面 · safety论文，上一届是 1 篇。
- 哪个会议的社会层面 · safety论文最多？
- ICML，2023–2026 年共 364 篇。