社会层面 · accountability transparency and interpretability论文趋势 2023–2026
AI 社会议题：accountability_transparency_and_interpretability
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,411 篇被归入该主题的论文。
主要结论
- 社会层面 · accountability transparency and interpretability论文从 2023 年的 301 篇增长到 2026 年的 1,357 篇，三年间扩大到约 4.5 倍。
- NeurIPS 是发社会层面 · accountability transparency and interpretability论文最多的会议，2023–2026 年共 1,275 篇，占四个会议总量的 37%。
- 交叉方向里涨得最快的是社会层面 · privacy：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 93 篇。
- 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的社会层面 · safety是 93 倍，社会层面 · accountability transparency and interpretability是 4.5 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 82 | 57 | 94 | 68 | 301 |
| 2024 | 255 | 83 | 152 | 99 | 589 |
| 2025 | 522 | 211 | 337 | 94 | 1,164 |
| 2026 | 416 | 292 | 541 | 108 | 1,357 |
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 Unifying Perspective on Language Model Interpretability
- ICML 2026$\texttt{PRISM}$:A 3D Probabilistic Neural Representation for Interpretable Shape Modeling
- ICLR 2026Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers
- CVPR 2026Beyond Matching to Tiles Bridging Unaligned Aerial and Satellite Views
- NeurIPS 2025$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
- ICML 2025(How) Can Transformers Predict Pseudo-Random Numbers?
- ICLR 2025Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers
- CVPR 2025Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability
- NeurIPS 20242D-OOB: Attributing Data Contribution Through Joint Valuation Framework
- ICML 2024Attention Meets Post-hoc Interpretability: A Mathematical Perspective
- ICLR 2024"What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data Selection
- CVPR 2024Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
- NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
- ICML 2023A Modern Look at the Relationship between Sharpness and Generalization
- ICLR 2023Deep Learning From Crowdsourced Labels: Coupled Cross-Entropy Minimization, Identifiability, and Regularization
- CVPR 2023Analyzing and Diagnosing Pose Estimation With Attributions
- NeurIPS 2026AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising
- ICML 2026$\texttt{ShaplEIG}$: Bayesian Experimental Design for Shapley Value Estimation
- ICLR 2026Bandits with Single-Peaked Preferences and Limited Resources
- CVPR 2026IEBGLAn Interpretability-Enhanced Brain Graph Learning Framework with LLM-Instructed Topology and
全部社会层面 · accountability transparency and interpretability论文
共 1,357 篇，第 5 / 28 页
- ICLR 2026First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation
- ICLR 2026Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
- ICLR 2026Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
- ICLR 2026FlexHiNM-GP: Flexible Hierarchical Pruning via Region Allocation and Channel Permutation
- ICLR 2026Flow Straight and Fast in Hilbert Space: Functional Rectified Flow
- ICLR 2026Flow-Disentangled Feature Importance
- ICLR 2026Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
- ICLR 2026FRABench and UFEval: Unified Fine-grained Evaluation with Task and Aspect Generalization
- ICLR 2026Fresh in memory: Training-order recency is linearly encoded in language model activations
- ICLR 2026From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
- ICLR 2026From Markov to Laplace: How Mamba In-Context Learns Markov Chains
- ICLR 2026From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
- ICLR 2026FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
- ICLR 2026Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition
- ICLR 2026GAVEL: Towards Rule-Based Safety through Activation Monitoring
- ICLR 2026GNN Explanations that do not Explain and How to find Them
- ICLR 2026GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching
- ICLR 2026GRADIEND: Feature Learning within Neural Networks Exemplified through Biases
- ICLR 2026Graph Mixing Additive Networks
- ICLR 2026Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
- ICLR 2026Hallucination Reduction with CASAL: Contrastive Activation Steering for Amortized Learning
- ICLR 2026Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs
- ICLR 2026Hidden Breakthroughs in Language Model Training
- ICLR 2026HiDivDrop: Vision Token Reduction in MLLMs via Late Injection and Differentiable Top-K
- ICLR 2026How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
- ICLR 2026How hard is learning to cut? Trade-offs and sample complexity
- ICLR 2026How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data
- ICLR 2026How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation.
- ICLR 2026How to Square Tensor Networks and Circuits Without Squaring Them
- ICLR 2026HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models
- ICLR 2026Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding
- ICLR 2026HUMOF: Human Motion Forecasting in Interactive Social Scenes
- ICLR 2026Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization
- ICLR 2026I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
- ICLR 2026Identifying and Evaluating Inactive Heads in Pretrained LLMs
- ICLR 2026In-Context Algebra
- ICLR 2026Influence Dynamics and Stagewise Data Attribution
- ICLR 2026INSTANT: Compressing Gradients and Activations for Resource-Efficient Training
- ICLR 2026Internal Planning in Language Models: Characterizing Horizon and Branch Awareness
- ICLR 2026Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
- ICLR 2026Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
- ICLR 2026Jet Expansions: Restructuring LLM Computation for Model Inspection
- ICLR 2026Joint Distribution–Informed Shapley Values for Sparse Counterfactual Explanations
- ICLR 2026Knowledge Editing with Subspace-Aware Key-Value Mappings
- ICLR 2026LABEL-FREE MITIGATION OF SPURIOUS CORRELATIONS IN VLMS USING SPARSE AUTOENCODERS
- ICLR 2026Language and Experience: A Computational Model of Social Learning in Complex Tasks
- ICLR 2026Language Models are Injective and Hence Invertible
- ICLR 2026Language Models Use Lookbacks to Track Beliefs
- ICLR 2026Language-Instructed Vision Embeddings for Controllable and Generalizable Perception
- ICLR 2026Latent Concept Disentanglement in Transformer-based Language Models
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 · accountability transparency and interpretability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": "social-accountability-transparency-and-interpretability"}
常见问题
- 2023–2026 年四大会议一共有多少篇社会层面 · accountability transparency and interpretability论文？
- 共 3,411 篇，按年份分别是 2023 年 301 篇、2024 年 589 篇、2025 年 1,164 篇、2026 年 1,357 篇。
- NeurIPS 2026 有多少篇社会层面 · accountability transparency and interpretability论文？
- NeurIPS 2026 有 416 篇社会层面 · accountability transparency and interpretability论文，上一届是 522 篇。
- ICLR 2026 有多少篇社会层面 · accountability transparency and interpretability论文？
- ICLR 2026 有 292 篇社会层面 · accountability transparency and interpretability论文，上一届是 211 篇。
- ICML 2026 有多少篇社会层面 · accountability transparency and interpretability论文？
- ICML 2026 有 541 篇社会层面 · accountability transparency and interpretability论文，上一届是 337 篇。
- CVPR 2026 有多少篇社会层面 · accountability transparency and interpretability论文？
- CVPR 2026 有 108 篇社会层面 · accountability transparency and interpretability论文，上一届是 94 篇。
- 哪个会议的社会层面 · accountability transparency and interpretability论文最多？
- NeurIPS，2023–2026 年共 1,275 篇。