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 9 of 26

401. NeurIPS 2026Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions
402. NeurIPS 2026Weird Generalization from Narrow Finetuning: Persona Shifts and Inductive Backdoors
403. NeurIPS 2026What Can Labels Alone Audit and Edit in Frozen Representations?
404. NeurIPS 2026What Cohort INRs Encode, and Where to Freeze Them
405. NeurIPS 2026What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules
406. NeurIPS 2026What Does a Sparse Autoencoder Feature Do? A Weight-Based Account
407. NeurIPS 2026What Makes a Good Path? Factoring Manifold Support and Path Geometry
408. NeurIPS 2026When and How to Canonize: a Generalization Perspective
409. NeurIPS 2026When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
410. NeurIPS 2026When Are Compositional Problems Learnable from Verifiable Rewards?
411. NeurIPS 2026When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
412. NeurIPS 2026When Poison Meets Structure: Topology-based Defense against Poisoning Attack on Graph-based Retrieval-Augmented Generation
413. NeurIPS 2026Where Should Society Draw the Line? A Social Choice Approach to Collective Consent
414. NeurIPS 2026Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
415. NeurIPS 2026Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
416. NeurIPS 2026Zeroth-Order Stackelberg Control in Combinatorial Congestion Games
417. NeurIPS 2025$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
418. NeurIPS 2025A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations
419. NeurIPS 2025A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
420. NeurIPS 2025A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
421. NeurIPS 2025A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
422. NeurIPS 2025A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding
423. NeurIPS 2025A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
424. NeurIPS 2025A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
425. NeurIPS 2025A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
426. NeurIPS 2025A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond
427. NeurIPS 2025A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances
428. NeurIPS 2025A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values
429. NeurIPS 2025Abstract Counterfactuals for Language Model Agents
430. NeurIPS 2025Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty
431. NeurIPS 2025AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs
432. NeurIPS 2025Accurate and Efficient Low-Rank Model Merging in Core Space
433. NeurIPS 2025AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
434. NeurIPS 2025AdaptGrad: Adaptive Sampling to Reduce Noise
435. NeurIPS 2025Adaptive Data Analysis for Growing Data
436. NeurIPS 2025Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
437. NeurIPS 2025Adaptive Sigmoid Clipping for Balancing the Direction–Magnitude Mismatch Trade-off in Differentially Private Learning
438. NeurIPS 2025Additive Models Explained: A Computational Complexity Approach
439. NeurIPS 2025Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
440. NeurIPS 2025Advancing Interpretability of CLIP Representations with Concept Surrogate Model
441. NeurIPS 2025Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
442. NeurIPS 2025AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference
443. NeurIPS 2025Aeolus: A Multi-structural Flight Delay Dataset
444. NeurIPS 2025Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
445. NeurIPS 2025Aligning Compound AI Systems via System-level DPO
446. NeurIPS 2025ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models
447. NeurIPS 2025AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
448. NeurIPS 2025Among Us: A Sandbox for Measuring and Detecting Agentic Deception
449. NeurIPS 2025An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
450. NeurIPS 2025An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise

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.