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

1,275 papers, page 19 of 26

901. NeurIPS 2025Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis
902. NeurIPS 2025Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization
903. NeurIPS 2025Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
904. NeurIPS 2025Unifying Proportional Fairness in Centroid and Non-Centroid Clustering
905. NeurIPS 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
906. NeurIPS 2025UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems
907. NeurIPS 2025Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
908. NeurIPS 2025Unlearning-Aware Minimization
909. NeurIPS 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
910. NeurIPS 2025Unveiling Concept Attribution in Diffusion Models
911. NeurIPS 2025Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization
912. NeurIPS 2025Unveiling the Uncertainty in Embodied and Operational Carbon of Large AI Models through a Probabilistic Carbon Accounting Model
913. NeurIPS 2025Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
914. NeurIPS 2025V-CECE: Visual Counterfactual Explanations via Conceptual Edits
915. NeurIPS 2025Vector Database Watermarking
916. NeurIPS 2025Versatile Transferable Unlearnable Example Generator
917. NeurIPS 2025Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
918. NeurIPS 2025Vision Transformers Don't Need Trained Registers
919. NeurIPS 2025VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
920. NeurIPS 2025Volume Transmission Implements Context Factorization to Target Online Credit Assignment and Enable Compositional Generalization
921. NeurIPS 2025WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
922. NeurIPS 2025Watermarking Autoregressive Image Generation
923. NeurIPS 2025What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
924. NeurIPS 2025What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
925. NeurIPS 2025What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses
926. NeurIPS 2025What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
927. NeurIPS 2025What Really is a Member? Discrediting Membership Inference via Poisoning
928. NeurIPS 2025When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
929. NeurIPS 2025When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration
930. NeurIPS 2025Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation
931. NeurIPS 2025Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations
932. NeurIPS 2025Why Do Some Language Models Fake Alignment While Others Don't?
933. NeurIPS 2025Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
934. NeurIPS 2025WMCopier: Forging Invisible Watermarks on Arbitrary Images
935. NeurIPS 2025World Models Should Prioritize the Unification of Physical and Social Dynamics
936. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
937. NeurIPS 2025Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model
938. NeurIPS 2025Zero-shot protein stability prediction by inverse folding models: a free energy interpretation
939. NeurIPS 20242D-OOB: Attributing Data Contribution Through Joint Valuation Framework
940. NeurIPS 20243-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
941. NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
942. NeurIPS 2024A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
943. NeurIPS 2024A Functional Extension of Semi-Structured Networks
944. NeurIPS 2024A hierarchical decomposition for explaining ML performance discrepancies
945. NeurIPS 2024A Polar coordinate system represents syntax in large language models
946. NeurIPS 2024A Simple and Optimal Approach for Universal Online Learning with Gradient Variations
947. NeurIPS 2024A Systematic Review of NeurIPS Dataset Management Practices
948. NeurIPS 2024A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
949. NeurIPS 2024A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs
950. NeurIPS 2024Abrupt Learning in Transformers: A Case Study on Matrix Completion

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.