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 292 篇，第 3 / 6 页

101. ICLR 2026Fresh in memory: Training-order recency is linearly encoded in language model activations
102. ICLR 2026From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
103. ICLR 2026From Markov to Laplace: How Mamba In-Context Learns Markov Chains
104. ICLR 2026From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
105. ICLR 2026FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
106. ICLR 2026Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition
107. ICLR 2026GAVEL: Towards Rule-Based Safety through Activation Monitoring
108. ICLR 2026GNN Explanations that do not Explain and How to find Them
109. ICLR 2026GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching
110. ICLR 2026GRADIEND: Feature Learning within Neural Networks Exemplified through Biases
111. ICLR 2026Graph Mixing Additive Networks
112. ICLR 2026Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
113. ICLR 2026Hallucination Reduction with CASAL: Contrastive Activation Steering for Amortized Learning
114. ICLR 2026Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs
115. ICLR 2026Hidden Breakthroughs in Language Model Training
116. ICLR 2026HiDivDrop: Vision Token Reduction in MLLMs via Late Injection and Differentiable Top-K
117. ICLR 2026How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
118. ICLR 2026How hard is learning to cut? Trade-offs and sample complexity
119. ICLR 2026How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data
120. ICLR 2026How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation.
121. ICLR 2026How to Square Tensor Networks and Circuits Without Squaring Them
122. ICLR 2026HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models
123. ICLR 2026Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding
124. ICLR 2026HUMOF: Human Motion Forecasting in Interactive Social Scenes
125. ICLR 2026Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization
126. ICLR 2026I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
127. ICLR 2026Identifying and Evaluating Inactive Heads in Pretrained LLMs
128. ICLR 2026In-Context Algebra
129. ICLR 2026Influence Dynamics and Stagewise Data Attribution
130. ICLR 2026INSTANT: Compressing Gradients and Activations for Resource-Efficient Training
131. ICLR 2026Internal Planning in Language Models: Characterizing Horizon and Branch Awareness
132. ICLR 2026Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
133. ICLR 2026Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
134. ICLR 2026Jet Expansions: Restructuring LLM Computation for Model Inspection
135. ICLR 2026Joint Distribution–Informed Shapley Values for Sparse Counterfactual Explanations
136. ICLR 2026Knowledge Editing with Subspace-Aware Key-Value Mappings
137. ICLR 2026LABEL-FREE MITIGATION OF SPURIOUS CORRELATIONS IN VLMS USING SPARSE AUTOENCODERS
138. ICLR 2026Language and Experience: A Computational Model of Social Learning in Complex Tasks
139. ICLR 2026Language Models are Injective and Hence Invertible
140. ICLR 2026Language Models Use Lookbacks to Track Beliefs
141. ICLR 2026Language-Instructed Vision Embeddings for Controllable and Generalizable Perception
142. ICLR 2026Latent Concept Disentanglement in Transformer-based Language Models
143. ICLR 2026Latent Planning Emerges with Scale
144. ICLR 2026LatentQA: Teaching LLMs to Decode Activations Into Natural Language
145. ICLR 2026Learning AND–OR Templates for Compositional Representation in Art and Design
146. ICLR 2026Learning for Highly Faithful Explainability
147. ICLR 2026Learning is Forgetting; LLM Training As Lossy Compression
148. ICLR 2026Learning multimodal dictionary decompositions with group-sparse autoencoders
149. ICLR 2026Learning on a Razor’s Edge: Identifiability and Singularity of Polynomial Neural Networks
150. ICLR 2026Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, 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。