对齐与安全论文趋势 2023–2026

RLHF、偏好优化、红队与安全对齐

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 4,558 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

对齐与安全论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202313887101112438
2024348156246125875
20254554733001351,363
20264806235512281,882

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

全部对齐与安全论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,421 篇，第 26 / 29 页

  1. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
  2. NeurIPS 2024Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
  3. NeurIPS 2024Understanding the Transferability of Representations via Task-Relatedness
  4. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
  5. NeurIPS 2024Unified Lexical Representation for Interpretable Visual-Language Alignment
  6. NeurIPS 2024UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
  7. NeurIPS 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
  8. NeurIPS 2024Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
  9. NeurIPS 2024UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
  10. NeurIPS 2024Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
  11. NeurIPS 2024Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
  12. NeurIPS 2024Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
  13. NeurIPS 2024Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
  14. NeurIPS 2024Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
  15. NeurIPS 2024Verifiably Robust Conformal Prediction
  16. NeurIPS 2024Verified Safe Reinforcement Learning for Neural Network Dynamic Models
  17. NeurIPS 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
  18. NeurIPS 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
  19. NeurIPS 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
  20. NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
  21. NeurIPS 2024Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
  22. NeurIPS 2024WeiPer: OOD Detection using Weight Perturbations of Class Projections
  23. NeurIPS 2024What If the Input is Expanded in OOD Detection?
  24. NeurIPS 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
  25. NeurIPS 2024When does perceptual alignment benefit vision representations?
  26. NeurIPS 2024When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
  27. NeurIPS 2024When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
  28. NeurIPS 2024Who's asking? User personas and the mechanics of latent misalignment
  29. NeurIPS 2024WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  30. NeurIPS 2024WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
  31. NeurIPS 2024Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
  32. NeurIPS 2024Your contrastive learning problem is secretly a distribution alignment problem
  33. NeurIPS 2024ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark
  34. NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
  35. NeurIPS 2023[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization
  36. NeurIPS 2023[Re] VAE Approximation Error: ELBO and Exponential Families
  37. NeurIPS 2023A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings
  38. NeurIPS 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
  39. NeurIPS 2023A Spectral Theory of Neural Prediction and Alignment
  40. NeurIPS 2023Abide by the law and follow the flow: conservation laws for gradient flows
  41. NeurIPS 2023Alignment with human representations supports robust few-shot learning
  42. NeurIPS 2023Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
  43. NeurIPS 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
  44. NeurIPS 2023BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
  45. NeurIPS 2023Behavior Alignment via Reward Function Optimization
  46. NeurIPS 2023Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
  47. NeurIPS 2023Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment
  48. NeurIPS 2023Bridging Discrete and Backpropagation: Straight-Through and Beyond
  49. NeurIPS 2023Cascading Contextual Assortment Bandits
  50. NeurIPS 2023Closing the gap between the upper bound and lower bound of Adam's iteration complexity

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 查对齐与安全在 NeurIPS 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": "alignment-and-safety"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇对齐与安全论文？
共 4,558 篇，按年份分别是 2023 年 438 篇、2024 年 875 篇、2025 年 1,363 篇、2026 年 1,882 篇。
NeurIPS 2026 有多少篇对齐与安全论文？
NeurIPS 2026 有 480 篇对齐与安全论文，上一届是 455 篇。
ICLR 2026 有多少篇对齐与安全论文？
ICLR 2026 有 623 篇对齐与安全论文，上一届是 473 篇。
ICML 2026 有多少篇对齐与安全论文？
ICML 2026 有 551 篇对齐与安全论文，上一届是 300 篇。
CVPR 2026 有多少篇对齐与安全论文？
CVPR 2026 有 228 篇对齐与安全论文，上一届是 135 篇。
哪个会议的对齐与安全论文最多？
NeurIPS，2023–2026 年共 1,421 篇。

「对齐与负责任 AI」下的其他主题