机制解释论文趋势 2023–2026

主要结论

• 机制解释论文从 2023 年的 17 篇增长到 2026 年的 138 篇，三年间扩大到约 8.1 倍。
• ICML 是发机制解释论文最多的会议，2023–2026 年共 119 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是深度学习 · large language models：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 23 篇。
• 在「可解释性」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的特征归因是 1.9 倍，机制解释是 8.1 倍。

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 2026A Mechanistic Interpretability Study of an Astronomical Foundation Model
• ICML 2026Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
• ICLR 2026Circuit Insights: Towards Interpretability Beyond Activations
• CVPR 2026CIGMA Causal Information-Gain Mechanistic Attribution of Attention Heads in Vision
• NeurIPS 2025Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
• ICML 2025Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
• ICLR 2025Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
• CVPR 2025Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
• NeurIPS 2024InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
• ICML 2024Mechanistic Neural Networks for Scientific Machine Learning
• ICLR 2024Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
• CVPR 2024SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology
• NeurIPS 2023A Logic for Expressing Log-Precision Transformers
• ICML 2023Mechanistic Mode Connectivity
• ICLR 2023Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small
• NeurIPS 2026Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
• ICML 2026CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
• ICLR 2026CLUE: Conflict-guided Localization for LLM Unlearning Framework
• CVPR 2026From Weights to Concepts Data-Free Interpretability of CLIP via Singular
• NeurIPS 2025Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models

全部机制解释论文

共 25 篇，第 1 / 1 页

1. NeurIPS 2024Algorithmic Capabilities of Random Transformers
2. NeurIPS 2024An Analysis of Tokenization: Transformers under Markov Data
3. NeurIPS 2024B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
4. NeurIPS 2024Compact Proofs of Model Performance via Mechanistic Interpretability
5. NeurIPS 2024Confidence Regulation Neurons in Language Models
6. NeurIPS 2024CoSy: Evaluating Textual Explanations of Neurons
7. NeurIPS 2024Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
8. NeurIPS 2024Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
9. NeurIPS 2024Grokking of Implicit Reasoning in Transformers: A Mechanistic Journey to the Edge of Generalization
10. NeurIPS 2024Hypothesis Testing the Circuit Hypothesis in LLMs
11. NeurIPS 2024Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
12. NeurIPS 2024InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
13. NeurIPS 2024InversionView: A General-Purpose Method for Reading Information from Neural Activations
14. NeurIPS 2024Iteration Head: A Mechanistic Study of Chain-of-Thought
15. NeurIPS 2024Linking In-context Learning in Transformers to Human Episodic Memory
16. NeurIPS 2024LLM Circuit Analyses Are Consistent Across Training and Scale
17. NeurIPS 2024Measuring Per-Unit Interpretability at Scale Without Humans
18. NeurIPS 2024Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
19. NeurIPS 2024Optimal ablation for interpretability
20. NeurIPS 2024Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics
21. NeurIPS 2024Refusal in Language Models Is Mediated by a Single Direction
22. NeurIPS 2024Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
23. NeurIPS 2024Transcoders find interpretable LLM feature circuits
24. NeurIPS 2024Truth is Universal: Robust Detection of Lies in LLMs
25. NeurIPS 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Study

常见问题

2023–2026 年四大会议一共有多少篇机制解释论文？

共 311 篇，按年份分别是 2023 年 17 篇、2024 年 49 篇、2025 年 107 篇、2026 年 138 篇。

NeurIPS 2026 有多少篇机制解释论文？

NeurIPS 2026 有 16 篇机制解释论文，上一届是 34 篇。

ICLR 2026 有多少篇机制解释论文？

ICLR 2026 有 46 篇机制解释论文，上一届是 38 篇。

ICML 2026 有多少篇机制解释论文？

ICML 2026 有 74 篇机制解释论文，上一届是 33 篇。

CVPR 2026 有多少篇机制解释论文？

CVPR 2026 有 2 篇机制解释论文，上一届是 2 篇。

哪个会议的机制解释论文最多？

ICML，2023–2026 年共 119 篇。