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 27 of 28

1301. NeurIPS 2026The Panel Complexity of Sortition: Is 12 Angry Men Enough?
1302. NeurIPS 2026The parameters in weight-sparse transformers are interpretable
1303. NeurIPS 2026The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment
1304. NeurIPS 2026The Rate-Distortion-Polysemanticity Tradeoff in SAEs
1305. NeurIPS 2026The Scaling Paradox of Tool-Calling LLM Agents Under Realistic MCP Faults
1306. NeurIPS 2026The Structural Bias of $\ell_2$-Regularized Cross-Entropy Heads in Class-Incremental Learning: Characterization, Limits, and a Gauge-Anchoring Fix
1307. NeurIPS 2026The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
1308. NeurIPS 2026Tight PAC-Bayes Generalisation Guarantees for Large Language Model Safety Monitoring
1309. NeurIPS 2026Topological Periodicity Test (TopPT) via Confidence Bound of Time-Delay Embeddings
1310. NeurIPS 2026Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time
1311. NeurIPS 2026Towards Differentially Private Reinforcement Learning with General Function Approximation
1312. NeurIPS 2026Towards Fair Graph Generation Without Sensitive Attribute
1313. NeurIPS 2026Towards Understanding and Measuring Cognitive Atrophy in LLM Behaviour
1314. NeurIPS 2026Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
1315. NeurIPS 2026Training Language Models to Explain Their Own Computations
1316. NeurIPS 2026Training ML Models with Predictable Failures
1317. NeurIPS 2026Transfer Entropy as a Measure of Information Flow in VLMs and LLMs
1318. NeurIPS 2026Transferring Visual Explainability from Self-Explaining to Prediction-Only Vision Transformers via Task Arithmetic
1319. NeurIPS 2026TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond
1320. NeurIPS 2026TriBet: Relative E-values for Online Machine-generated Text Detection
1321. NeurIPS 2026TRIDENT: Post-Selection Evidence Accountability for Token-Efficient RAG
1322. NeurIPS 2026TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation
1323. NeurIPS 2026Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
1324. NeurIPS 2026Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning
1325. NeurIPS 2026Uncovering the latent structure of interwoven population and temporal codes
1326. NeurIPS 2026Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
1327. NeurIPS 2026Understanding and Mitigating Under-Confidence in GNNs from the Final Layer
1328. NeurIPS 2026Understanding Private Evolution as Learning-Augmented Clustering
1329. NeurIPS 2026Uniform Diffusion Models revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
1330. NeurIPS 2026Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA
1331. NeurIPS 2026Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters
1332. NeurIPS 2026Unifying Partner and Environment Diversity to Improve Human-AI Coordination
1333. NeurIPS 2026UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
1334. NeurIPS 2026Unsupervised Unlearnable Segmentation via Semantic Structure Disruption
1335. NeurIPS 2026Untrusted Content Masking for Web Agents with Security Guarantees
1336. NeurIPS 2026Values Are Not Single Labels: Distributional Value Profiling Across Groups and Contexts
1337. NeurIPS 2026Verified-Source Authority Is Not Generic Sycophancy: Cue-Family Decomposition of LLM Compliance
1338. NeurIPS 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
1339. NeurIPS 2026VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models
1340. NeurIPS 2026Watermarking as a Learned Intrinsic Property of Diffusion Models
1341. NeurIPS 2026Watermarking Without Standards Is Not AI Governance
1342. NeurIPS 2026Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions
1343. NeurIPS 2026Weird Generalization from Narrow Finetuning: Persona Shifts and Inductive Backdoors
1344. NeurIPS 2026What Can Labels Alone Audit and Edit in Frozen Representations?
1345. NeurIPS 2026What Cohort INRs Encode, and Where to Freeze Them
1346. NeurIPS 2026What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules
1347. NeurIPS 2026What Does a Sparse Autoencoder Feature Do? A Weight-Based Account
1348. NeurIPS 2026What Makes a Good Path? Factoring Manifold Support and Path Geometry
1349. NeurIPS 2026When and How to Canonize: a Generalization Perspective
1350. NeurIPS 2026When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds

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.