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

1,164 papers, page 23 of 24

1101. NeurIPS 2025Tight Bounds on the Distortion of Randomized and Deterministic Distributed Voting
1102. NeurIPS 2025Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
1103. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
1104. NeurIPS 2025Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
1105. NeurIPS 2025TopER: Topological Embeddings in Graph Representation Learning
1106. NeurIPS 2025Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement
1107. NeurIPS 2025Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
1108. NeurIPS 2025Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
1109. NeurIPS 2025Towards Irreversible Attack: Fooling Scene Text Recognition via Multi-Population Coevolution Search
1110. NeurIPS 2025Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
1111. NeurIPS 2025ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
1112. NeurIPS 2025TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents
1113. NeurIPS 2025Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
1114. NeurIPS 2025Training-free Detection of AI-generated images via Cropping Robustness
1115. NeurIPS 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
1116. NeurIPS 2025Transferring Linear Features Across Language Models With Model Stitching
1117. NeurIPS 2025Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
1118. NeurIPS 2025Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models
1119. NeurIPS 2025TRAP: Targeted Redirecting of Agentic Preferences
1120. NeurIPS 2025TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
1121. NeurIPS 2025Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
1122. NeurIPS 2025UMoE: Unifying Attention and FFN with Shared Experts
1123. NeurIPS 2025Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
1124. NeurIPS 2025Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
1125. NeurIPS 2025Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations
1126. NeurIPS 2025Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness
1127. NeurIPS 2025Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis
1128. NeurIPS 2025Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization
1129. NeurIPS 2025Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
1130. NeurIPS 2025Unifying Proportional Fairness in Centroid and Non-Centroid Clustering
1131. NeurIPS 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
1132. NeurIPS 2025UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems
1133. NeurIPS 2025Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
1134. NeurIPS 2025Unlearning-Aware Minimization
1135. NeurIPS 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
1136. NeurIPS 2025Unveiling Concept Attribution in Diffusion Models
1137. NeurIPS 2025Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization
1138. NeurIPS 2025Unveiling the Uncertainty in Embodied and Operational Carbon of Large AI Models through a Probabilistic Carbon Accounting Model
1139. NeurIPS 2025Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
1140. NeurIPS 2025V-CECE: Visual Counterfactual Explanations via Conceptual Edits
1141. NeurIPS 2025Vector Database Watermarking
1142. NeurIPS 2025Versatile Transferable Unlearnable Example Generator
1143. NeurIPS 2025Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
1144. NeurIPS 2025Vision Transformers Don't Need Trained Registers
1145. NeurIPS 2025VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
1146. NeurIPS 2025Volume Transmission Implements Context Factorization to Target Online Credit Assignment and Enable Compositional Generalization
1147. NeurIPS 2025WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
1148. NeurIPS 2025Watermarking Autoregressive Image Generation
1149. NeurIPS 2025What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
1150. NeurIPS 2025What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

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.