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

1,124 papers, page 18 of 23

851. ICML 2025Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models
852. ICML 2025Towards Memorization Estimation: Fast, Formal and Free
853. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
854. ICML 2025Towards Trustworthy Federated Learning with Untrusted Participants
855. ICML 2025Tracking The Best Expert Privately
856. ICML 2025Trustworthy Machine Learning through Data-Specific Indistinguishability
857. ICML 2025Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations
858. ICML 2025Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
859. ICML 2025Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
860. ICML 2025Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
861. ICML 2025Understanding Fixed Predictions via Confined Regions
862. ICML 2025Understanding Model Ensemble in Transferable Adversarial Attack
863. ICML 2025Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism
864. ICML 2025Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
865. ICML 2025Validating Mechanistic Interpretations: An Axiomatic Approach
866. ICML 2025Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models
867. ICML 2025Vision-Language Models Create Cross-Modal Task Representations
868. ICML 2025Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
869. ICML 2025Weak-to-Strong Jailbreaking on Large Language Models
870. ICML 2025Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
871. ICML 2025What makes an Ensemble (Un) Interpretable?
872. ICML 2025When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
873. ICML 2025Which Attention Heads Matter for In-Context Learning?
874. ICML 2025WILTing Trees: Interpreting the Distance Between MPNN Embeddings
875. ICML 2025WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models
876. ICML 2025X-Hacking: The Threat of Misguided AutoML
877. ICML 2025XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
878. ICML 2025You Get What You Give: Reciprocally Fair Federated Learning
879. ICML 2024A connection between Tempering and Entropic Mirror Descent
880. ICML 2024A Multimodal Automated Interpretability Agent
881. ICML 2024A Persuasive Approach to Combating Misinformation
882. ICML 2024A Unified View of FANOVA: A Comprehensive Bayesian Framework for Component Selection and Estimation
883. ICML 2024Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion
884. ICML 2024Active Ranking and Matchmaking, with Perfect Matchings
885. ICML 2024AI Alignment with Changing and Influenceable Reward Functions
886. ICML 2024AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training
887. ICML 2024An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization
888. ICML 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
889. ICML 2024Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data
890. ICML 2024Attention Meets Post-hoc Interpretability: A Mathematical Perspective
891. ICML 2024Balanced Resonate-and-Fire Neurons
892. ICML 2024Benchmarking Deletion Metrics with the Principled Explanations
893. ICML 2024Bootstrapping Fisher Market Equilibrium and First-Price Pacing Equilibrium
894. ICML 2024Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
895. ICML 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
896. ICML 2024Can Machines Learn the True Probabilities?
897. ICML 2024Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
898. ICML 2024Clifford-Steerable Convolutional Neural Networks
899. ICML 2024Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
900. ICML 2024Codebook Features: Sparse and Discrete Interpretability for Neural Networks

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.