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 13 of 24

601. ICML 2025The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
602. ICML 2025The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
603. ICML 2025The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
604. ICML 2025The Lock-in Hypothesis: Stagnation by Algorithm
605. ICML 2025The Power of Random Features and the Limits of Distribution-Free Gradient Descent
606. ICML 2025The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
607. ICML 2025The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
608. ICML 2025The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
609. ICML 2025The Value of Prediction in Identifying the Worst-Off
610. ICML 2025TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
611. ICML 2025Topological Signatures of Adversaries in Multimodal Alignments
612. ICML 2025Towards Attributions of Input Variables in a Coalition
613. ICML 2025Towards Black-Box Membership Inference Attack for Diffusion Models
614. ICML 2025Towards flexible perception with visual memory
615. ICML 2025Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models
616. ICML 2025Towards Memorization Estimation: Fast, Formal and Free
617. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
618. ICML 2025Towards Trustworthy Federated Learning with Untrusted Participants
619. ICML 2025Tracking The Best Expert Privately
620. ICML 2025Trustworthy Machine Learning through Data-Specific Indistinguishability
621. ICML 2025Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations
622. ICML 2025Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
623. ICML 2025Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
624. ICML 2025Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
625. ICML 2025Understanding Fixed Predictions via Confined Regions
626. ICML 2025Understanding Model Ensemble in Transferable Adversarial Attack
627. ICML 2025Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism
628. ICML 2025Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
629. ICML 2025Validating Mechanistic Interpretations: An Axiomatic Approach
630. ICML 2025Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models
631. ICML 2025Vision-Language Models Create Cross-Modal Task Representations
632. ICML 2025Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
633. ICML 2025Weak-to-Strong Jailbreaking on Large Language Models
634. ICML 2025Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
635. ICML 2025What makes an Ensemble (Un) Interpretable?
636. ICML 2025When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
637. ICML 2025Which Attention Heads Matter for In-Context Learning?
638. ICML 2025WILTing Trees: Interpreting the Distance Between MPNN Embeddings
639. ICML 2025WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models
640. ICML 2025X-Hacking: The Threat of Misguided AutoML
641. ICML 2025XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
642. ICML 2025You Get What You Give: Reciprocally Fair Federated Learning
643. NeurIPS 2025$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
644. NeurIPS 2025A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations
645. NeurIPS 2025A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
646. NeurIPS 2025A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
647. NeurIPS 2025A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
648. NeurIPS 2025A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding
649. NeurIPS 2025A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
650. NeurIPS 2025A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation

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.