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 11 / 29 页

  1. NeurIPS 2025Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
  2. NeurIPS 2025AI-Generated Video Detection via Perceptual Straightening
  3. NeurIPS 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
  4. NeurIPS 2025Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
  5. NeurIPS 2025Aligning Compound AI Systems via System-level DPO
  6. NeurIPS 2025Aligning Text to Image in Diffusion Models is Easier Than You Think
  7. NeurIPS 2025Aligning Transformers with Continuous Feedback via Energy Rank Alignment
  8. NeurIPS 2025Alignment of Large Language Models with Constrained Learning
  9. NeurIPS 2025AliO: Output Alignment Matters in Long-Term Time Series Forecasting
  10. NeurIPS 2025ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models
  11. NeurIPS 2025Among Us: A Sandbox for Measuring and Detecting Agentic Deception
  12. NeurIPS 2025An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds
  13. NeurIPS 2025Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
  14. NeurIPS 2025Angular Steering: Behavior Control via Rotation in Activation Space
  15. NeurIPS 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
  16. NeurIPS 2025Ask a Strong LLM Judge when Your Reward Model is Uncertain
  17. NeurIPS 2025Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
  18. NeurIPS 2025Attention Mechanism, Max-Affine Partition, and Universal Approximation
  19. NeurIPS 2025Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
  20. NeurIPS 2025Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
  21. NeurIPS 2025AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving
  22. NeurIPS 2025AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
  23. NeurIPS 2025Avoiding exp(R) scaling in RLHF through Preference-based Exploration
  24. NeurIPS 2025Backdoor Cleaning without External Guidance in MLLM Fine-tuning
  25. NeurIPS 2025BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
  26. NeurIPS 2025Bag of Tricks for Inference-time Computation of LLM Reasoning
  27. NeurIPS 2025Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled Learning
  28. NeurIPS 2025Bandit and Delayed Feedback in Online Structured Prediction
  29. NeurIPS 2025Best-of-N Jailbreaking
  30. NeurIPS 2025Better Estimation of the Kullback--Leibler Divergence Between Language Models
  31. NeurIPS 2025Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models
  32. NeurIPS 2025Beyond Oracle: Verifier-Supervision for Instruction Hierarchy in Reasoning and Instruction-Tuned LLMs
  33. NeurIPS 2025Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
  34. NeurIPS 2025Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
  35. NeurIPS 2025BLEUBERI: BLEU is a surprisingly effective reward for instruction following
  36. NeurIPS 2025Boosting Adversarial Transferability with Spatial Adversarial Alignment
  37. NeurIPS 2025Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models
  38. NeurIPS 2025Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks
  39. NeurIPS 2025Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
  40. NeurIPS 2025Bridging Theory and Practice in Link Representation with Graph Neural Networks
  41. NeurIPS 2025Bridging Time and Linguistics: LLMs as Time Series Analyzer through Symbolization and Segmentation
  42. NeurIPS 2025C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails
  43. NeurIPS 2025Calibrating Translation Decoding with Quality Estimation on LLMs
  44. NeurIPS 2025CaliGCL: Calibrated Graph Contrastive Learning via Partitioned Similarity and Consistency Discrimination
  45. NeurIPS 2025CALM: Culturally Self-Aware Language Models
  46. NeurIPS 2025CAMILA: Context-Aware Masking for Image Editing with Language Alignment
  47. NeurIPS 2025Can DPO Learn Diverse Human Values? A Theoretical Scaling Law
  48. NeurIPS 2025CARE: Decoding-Time Safety Alignment via Rollback and Introspection Intervention
  49. NeurIPS 2025CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs
  50. NeurIPS 2025Certifying Concavity and Monotonicity in Games via Sum-of-Squares Hierarchies

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