Social aspects · accountability transparency and interpretability papers, 2023–2026

Key findings

• Social aspects · accountability transparency and interpretability went from 301 papers in 2023 to 1,357 in 2026, roughly 4.5x in three years.
• NeurIPS publishes the most Social aspects · accountability transparency and interpretability work: 1,275 papers from 2023 to 2026, 37% of the four-venue total.
• The fastest-growing overlap is with Social aspects · privacy: papers tagged with both rose from 0 in 2023 to 93 in 2026.
• Among the 5 topics under Alignment and Responsible AI, it ranks #2 by 2026 paper count; the fastest grower in the group, Social aspects · safety, is up 93x versus 4.5x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Social aspects · accountability transparency and interpretability papers

3,411 papers, page 5 of 69

201. ICLR 2026First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation
202. ICLR 2026Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
203. ICLR 2026Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
204. ICLR 2026FlexHiNM-GP: Flexible Hierarchical Pruning via Region Allocation and Channel Permutation
205. ICLR 2026Flow Straight and Fast in Hilbert Space: Functional Rectified Flow
206. ICLR 2026Flow-Disentangled Feature Importance
207. ICLR 2026Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
208. ICLR 2026FRABench and UFEval: Unified Fine-grained Evaluation with Task and Aspect Generalization
209. ICLR 2026Fresh in memory: Training-order recency is linearly encoded in language model activations
210. ICLR 2026From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
211. ICLR 2026From Markov to Laplace: How Mamba In-Context Learns Markov Chains
212. ICLR 2026From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
213. ICLR 2026FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
214. ICLR 2026Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition
215. ICLR 2026GAVEL: Towards Rule-Based Safety through Activation Monitoring
216. ICLR 2026GNN Explanations that do not Explain and How to find Them
217. ICLR 2026GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching
218. ICLR 2026GRADIEND: Feature Learning within Neural Networks Exemplified through Biases
219. ICLR 2026Graph Mixing Additive Networks
220. ICLR 2026Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
221. ICLR 2026Hallucination Reduction with CASAL: Contrastive Activation Steering for Amortized Learning
222. ICLR 2026Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs
223. ICLR 2026Hidden Breakthroughs in Language Model Training
224. ICLR 2026HiDivDrop: Vision Token Reduction in MLLMs via Late Injection and Differentiable Top-K
225. ICLR 2026How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
226. ICLR 2026How hard is learning to cut? Trade-offs and sample complexity
227. ICLR 2026How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data
228. ICLR 2026How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation.
229. ICLR 2026How to Square Tensor Networks and Circuits Without Squaring Them
230. ICLR 2026HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models
231. ICLR 2026Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding
232. ICLR 2026HUMOF: Human Motion Forecasting in Interactive Social Scenes
233. ICLR 2026Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization
234. ICLR 2026I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
235. ICLR 2026Identifying and Evaluating Inactive Heads in Pretrained LLMs
236. ICLR 2026In-Context Algebra
237. ICLR 2026Influence Dynamics and Stagewise Data Attribution
238. ICLR 2026INSTANT: Compressing Gradients and Activations for Resource-Efficient Training
239. ICLR 2026Internal Planning in Language Models: Characterizing Horizon and Branch Awareness
240. ICLR 2026Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
241. ICLR 2026Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
242. ICLR 2026Jet Expansions: Restructuring LLM Computation for Model Inspection
243. ICLR 2026Joint Distribution–Informed Shapley Values for Sparse Counterfactual Explanations
244. ICLR 2026Knowledge Editing with Subspace-Aware Key-Value Mappings
245. ICLR 2026LABEL-FREE MITIGATION OF SPURIOUS CORRELATIONS IN VLMS USING SPARSE AUTOENCODERS
246. ICLR 2026Language and Experience: A Computational Model of Social Learning in Complex Tasks
247. ICLR 2026Language Models are Injective and Hence Invertible
248. ICLR 2026Language Models Use Lookbacks to Track Beliefs
249. ICLR 2026Language-Instructed Vision Embeddings for Controllable and Generalizable Perception
250. ICLR 2026Latent Concept Disentanglement in Transformer-based Language Models

FAQ

How many Social aspects · accountability transparency and interpretability papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

3,411 in total: 301 in 2023, 589 in 2024, 1,164 in 2025, 1,357 in 2026.

How many Social aspects · accountability transparency and interpretability papers are at NeurIPS 2026?

NeurIPS 2026 has 416 Social aspects · accountability transparency and interpretability papers, versus 522 the year before.

How many Social aspects · accountability transparency and interpretability papers are at ICLR 2026?

ICLR 2026 has 292 Social aspects · accountability transparency and interpretability papers, versus 211 the year before.

How many Social aspects · accountability transparency and interpretability papers are at ICML 2026?

ICML 2026 has 541 Social aspects · accountability transparency and interpretability papers, versus 337 the year before.

How many Social aspects · accountability transparency and interpretability papers are at CVPR 2026?

CVPR 2026 has 108 Social aspects · accountability transparency and interpretability papers, versus 94 the year before.

Which conference publishes the most Social aspects · accountability transparency and interpretability papers?

NeurIPS, with 1,275 papers from 2023 to 2026.