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 416 篇，第 4 / 9 页

151. NeurIPS 2026Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
152. NeurIPS 2026Harbor Adapters and Harbor-Mix: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
153. NeurIPS 2026HARC: Coupling Harmfulness and Refusal Capabilities for Robust Safety Alignment
154. NeurIPS 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
155. NeurIPS 2026Hierarchical Agglomerative Clustering via Relaxed Representatives
156. NeurIPS 2026Hierarchical Conformal Classification
157. NeurIPS 2026How are linear representations learned? Exact solutions to the dynamics of abstraction
158. NeurIPS 2026How Do Agentic LLMs Decide to Call Tools? A Scaffold Default Controlled by Suppression
159. NeurIPS 2026How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location
160. NeurIPS 2026How do Small Transformer Models Learn Hard Math Tasks?
161. NeurIPS 2026How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness
162. NeurIPS 2026How Likely Are Voting Rules Equitable?
163. NeurIPS 2026Human-AI Teaming Through the Lens of Calibration
164. NeurIPS 2026Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes
165. NeurIPS 2026Hyperbolic Concept Bottleneck Models
166. NeurIPS 2026Idempotency Exposes Consistency Problems in Sparse Autoencoders
167. NeurIPS 2026Improved State Mixing in Higher-order and Block Diagonal Linear Recurrent Networks
168. NeurIPS 2026Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
169. NeurIPS 2026Information Loss and Disparate Effects in Network Embeddings
170. NeurIPS 2026Integral Probability Boundaries
171. NeurIPS 2026Internal Safety Collapse in Frontier Large Language Models
172. NeurIPS 2026Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
173. NeurIPS 2026Interpreting Latent Protein Language Model Features with Geometric Annotations
174. NeurIPS 2026Intersectional Fairness via Mixed-Integer Optimization
175. NeurIPS 2026Introspective Coupling: LMs Learn to Explain Themselves Better Than Their Training Targets
176. NeurIPS 2026Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
177. NeurIPS 2026Invariance and Body-Order Compose Additively: Minimax Rates on $\mathrm{SO}(3)^n$
178. NeurIPS 2026Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies
179. NeurIPS 2026Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic
180. NeurIPS 2026Joint Learning of Hierarchical Neural Options and Abstract World Model
181. NeurIPS 2026Jointly Reinforcing Diversity and Quality in Language Model Generations
182. NeurIPS 2026Jointly Robust Fairness: Overcoming Simultaneous Label and Attribute Noise
183. NeurIPS 2026JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors
184. NeurIPS 2026KiteNorm: Variance Regularisation for Stable and Scalable Post-LN Transformers
185. NeurIPS 2026Learning a Unified Cross-Model Semantic Dictionary via Gated Bottleneck Sparse Autoencoders
186. NeurIPS 2026Learning Data-free Universal Adversarial Perturbation with Hybrid Priors and Gradient-Guided Sharpness Regularization
187. NeurIPS 2026Learning Distributions from Multiple Data Providers
188. NeurIPS 2026Learning Reach-Set Geometry for Tighter Probabilistic Neural Network Verification
189. NeurIPS 2026Learning the Signature of Memorization in Autoregressive Language Models
190. NeurIPS 2026Learning to Decide with AI Assistance under Human-Alignment
191. NeurIPS 2026Learning-Augmented Mechanism Design for Facility Location under $L_p$-Norm Social Costs
192. NeurIPS 2026Leviathan: Decoupling Input and Output Representations in Language Models
193. NeurIPS 2026Limits and Potential of Score-Based Data Valuation: Redundancy, Complementarity, and Non-Monotonicity
194. NeurIPS 2026LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
195. NeurIPS 2026Literati: Towards Anytime Optimal Shape Generalized Trees via AO*
196. NeurIPS 2026LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
197. NeurIPS 2026LLM Rheology: Auditing Refusal Geometry in Aligned Language Models
198. NeurIPS 2026LLMs can construct powerful representations and streamline sample-efficient supervised learning
199. NeurIPS 2026Local FDR Membership Inference Attacks: Multiple Testing and the Role of Ridge Regularization
200. NeurIPS 2026Localizing and Repairing Sparse-Prompt Failure in SAM Decoders via Box-to-Point Counterfactual

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。