社会层面 · accountability transparency and interpretability论文趋势 2023–2026

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。

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 3,411 篇，第 4 / 69 页

151. ICLR 2026Composable Sparse Subnetworks via Maximum-Entropy Principle
152. ICLR 2026Concepts' Information Bottleneck Models
153. ICLR 2026Conjuring Semantic Similarity
154. ICLR 2026ContextBench: Modifying Contexts for Targeted Latent Activation and Behaviour Elicitation
155. ICLR 2026Controlling Repetition in Protein Language Models
156. ICLR 2026Copy-Paste to Mitigate Large Language Model Hallucinations
157. ICLR 2026Correlations in the Data Lead to Semantically Rich Feature Geometry Under Superposition
158. ICLR 2026Counterfactual Explanations on Robust Perceptual Geodesics
159. ICLR 2026Critical Confabulation: Can LLMs Hallucinate for Social Good?
160. ICLR 2026Cross-Modal Redundancy and the Geometry of Vision–Language Embeddings
161. ICLR 2026CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model
162. ICLR 2026Debugging Concept Bottleneck Models through Removal and Retraining
163. ICLR 2026Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal Convergence
164. ICLR 2026Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
165. ICLR 2026Deconstructing Positional Information: From Attention Logits to Training Biases
166. ICLR 2026Decoupling Positional and Symbolic Attention in Transformers
167. ICLR 2026Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability
168. ICLR 2026Deterministic Bounds and Random Estimates of Metric Tensors on Neuromanifolds
169. ICLR 2026Discovering and Steering Interpretable Concepts in Large Generative Music Models
170. ICLR 2026Dissecting Representation Misalignment in Contrastive Learning via Influence Function
171. ICLR 2026Does Higher Interpretability Imply Better Utility? A Pairwise Analysis on Sparse Autoencoders
172. ICLR 2026DR-GGAD: Dual Residual Centering for Mitigating Anomaly Non‑Discriminativity in Generalist Graph Anomaly Detection
173. ICLR 2026DTP: Delta-Guided Two Stage Pruning for Mamba-based Multimodal Large Language Models
174. ICLR 2026Efficient Testing for Correlation Clustering: Improved Algorithms and Optimal Bounds
175. ICLR 2026ELEPHANT: Measuring and understanding social sycophancy in LLMs
176. ICLR 2026ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
177. ICLR 2026Emergent Misalignment is Easy, Narrow Misalignment is Hard
178. ICLR 2026Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models
179. ICLR 2026Enforcing Axioms for AI Alignment under Loss-Based Rules
180. ICLR 2026Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
181. ICLR 2026Escaping Low-Rank Traps: Interpretable Visual Concept Learning via Implicit Vector Quantization
182. ICLR 2026Evaluating Data Influence in Meta Learning
183. ICLR 2026Evaluating SAE interpretability without generating explanations
184. ICLR 2026Evaluating Text Creativity across Diverse Domains: a Dataset and Large Language Model Evaluator
185. ICLR 2026Every Language Model Has a Forgery-Resistant Signature
186. ICLR 2026Evolution and compression in LLMs: on the emergence of human-aligned categorization
187. ICLR 2026Evolution of Concepts in Language Model Pre-Training
188. ICLR 2026EXP-Bench: Can AI Conduct AI Research Experiments?
189. ICLR 2026Expert Heads: Robust Evidence Identification for Large Language Models
190. ICLR 2026Explainable Mixture Models through Differentiable Rule Learning
191. ICLR 2026Exploratory Causal Inference in SAEnce
192. ICLR 2026Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts
193. ICLR 2026f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
194. ICLR 2026Fair Policy Aggregation from Standard Policy Optimization
195. ICLR 2026Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
196. ICLR 2026FAME: $\underline{F}$ormal $\underline{A}$bstract $\underline{M}$inimal $\underline{E}$xplanation for neural networks
197. ICLR 2026Fantastic Pretraining Optimizers and Where to Find Them
198. ICLR 2026Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry
199. ICLR 2026Feature segregation by signed weights in artificial vision systems and biological models
200. ICLR 2026Financial fraud collusion among generative AI agents in social networks

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。