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

1,357 papers, page 17 of 28

801. ICML 2026Revisiting Neural Processes via Fourier Transform and Volterra Series
802. ICML 2026Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
803. ICML 2026Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
804. ICML 2026Riemannian Neural Optimal Transport
805. ICML 2026Ripple Perturbations Through Structure: Likelihood-Constrained Adversarial Attacks on Heterogeneous Tabular Data
806. ICML 2026RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
807. ICML 2026Robust AI Evaluation through Maximal Lotteries
808. ICML 2026Robust Human-AI Complementarity under Uncertainty
809. ICML 2026Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions
810. ICML 2026Robust Stochastic Gradient Posterior Sampling with Lattice Based Discretisation
811. ICML 2026Robust Strategic Classification under Decision-Dependent Cost Uncertainty
812. ICML 2026Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling
813. ICML 2026RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
814. ICML 2026SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
815. ICML 2026SAEs-BrainMap: Unveiling the Emergence of Specialized Concepts in Deep Models via Brain Alignment
816. ICML 2026Same Question, Different Lies: Cross-Context Consistency (C³) for Black-Box Sandbagging Detection
817. ICML 2026Scalable and Interpretable Representation Alignment with Ordinal Similarity
818. ICML 2026Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
819. ICML 2026SecCodePRM: A Process Reward Model for Code Security
820. ICML 2026Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense
821. ICML 2026Seeing to Generalize: How Visual Data Corrects Binding Shortcuts
822. ICML 2026Selective Disclosure Watermarking for Large Language Models
823. ICML 2026Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews
824. ICML 2026Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
825. ICML 2026SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
826. ICML 2026Shared Lexical Task Representations Explain Behavioral Variability In LLMs
827. ICML 2026Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms
828. ICML 2026Sharper Generalization Guarantees for Asynchronous SGD: Beyond Lipschitzness, Smoothness and Data Homogeneity
829. ICML 2026Shuffling-Aware Optimization for Private Vector Mean Estimation
830. ICML 2026Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
831. ICML 2026Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
832. ICML 2026Singular Vectors of Attention Heads Align with Features
833. ICML 2026SLIM: Secure and Efficient Inference for Large Language Models on Untrusted Devices via TEEs
834. ICML 2026Social Hippocampus Memory Learning
835. ICML 2026Solving Positive Linear Programs with Differential Privacy
836. ICML 2026SOPE: Situation-Aware and Statistically Indistinguishable Privacy Exfiltration for MCP-enabled Agents
837. ICML 2026Sparse and Faithful Local Explanations with Piecewise Linear Surrogates
838. ICML 2026Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
839. ICML 2026Sparse Relaxed-Lasso Steering: Automatic Sparse Autoencoder Feature Selection for Precise Image Editing
840. ICML 2026Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
841. ICML 2026SpatialJB: How Text Distribution Art Becomes The "Jailbreak Key" for LLM Guardrails
842. ICML 2026Spherical Steering: Geometry-Aware Activation Rotation for Language Models
843. ICML 2026Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
844. ICML 2026Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning
845. ICML 2026Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
846. ICML 2026ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
847. ICML 2026State Space Model with Continuous Limit of HiPPO Matrix: Eigenvalue Analysis and Explicit Solution Formula
848. ICML 2026State-Dependent Safety Failures in Multi-Turn Language Model Interaction
849. ICML 2026Statistical Consistency and Generalization of Contrastive Representation Learning
850. ICML 2026Steering at the Source: Style Modulation Heads for Robust Persona Control

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.