社会层面 · accountability transparency and interpretability论文趋势 2023–2026

主要结论

• 社会层面 · accountability transparency and interpretability论文从 2023 年的 301 篇增长到 2026 年的 1,357 篇，三年间扩大到约 4.5 倍。
• NeurIPS 是发社会层面 · accountability transparency and interpretability论文最多的会议，2023–2026 年共 1,275 篇，占四个会议总量的 37%。
• 交叉方向里涨得最快的是社会层面 · privacy：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 93 篇。
• 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的社会层面 · safety是 93 倍，社会层面 · accountability transparency and interpretability是 4.5 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部社会层面 · accountability transparency and interpretability论文

共 643 篇，第 7 / 13 页

301. ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
302. ICLR 2025Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
303. ICLR 2025Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
304. ICLR 2025Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
305. ICLR 2025Ask, and it shall be given: On the Turing completeness of prompting
306. ICLR 2025Attention as a Hypernetwork
307. ICLR 2025Attention with Markov: A Curious Case of Single-layer Transformers
308. ICLR 2025AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
309. ICLR 2025Attributing Culture-Conditioned Generations to Pretraining Corpora
310. ICLR 2025Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
311. ICLR 2025Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability
312. ICLR 2025Bilinear MLPs enable weight-based mechanistic interpretability
313. ICLR 2025Boosting Methods for Interval-censored Data with Regression and Classification
314. ICLR 2025Boosting the visual interpretability of CLIP via adversarial fine-tuning
315. ICLR 2025BrainOOD: Out-of-distribution Generalizable Brain Network Analysis
316. ICLR 2025Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
317. ICLR 2025Can Transformers Do Enumerative Geometry?
318. ICLR 2025Capability Localization: Capabilities Can be Localized rather than Individual Knowledge
319. ICLR 2025Capturing the Temporal Dependence of Training Data Influence
320. ICLR 2025Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
321. ICLR 2025Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources
322. ICLR 2025Competition Dynamics Shape Algorithmic Phases of In-Context Learning
323. ICLR 2025Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement
324. ICLR 2025Concept Bottleneck Large Language Models
325. ICLR 2025Controllable Context Sensitivity and the Knob Behind It
326. ICLR 2025Controlling Language and Diffusion Models by Transporting Activations
327. ICLR 2025Counterfactual Concept Bottleneck Models
328. ICLR 2025Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
329. ICLR 2025Data Shapley in One Training Run
330. ICLR 2025Data-centric Prediction Explanation via Kernelized Stein Discrepancy
331. ICLR 2025Deep Networks Learn Features From Local Discontinuities in the Label Function
332. ICLR 2025DICE: Data Influence Cascade in Decentralized Learning
333. ICLR 2025Differentiable Rule Induction from Raw Sequence Inputs
334. ICLR 2025Differential learning kinetics govern the transition from memorization to generalization during in-context learning
335. ICLR 2025Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
336. ICLR 2025Diverse Preference Learning for Capabilities and Alignment
337. ICLR 2025Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
338. ICLR 2025Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?
339. ICLR 2025Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
340. ICLR 2025Dynamic Assortment Selection and Pricing with Censored Preference Feedback
341. ICLR 2025Efficient and Accurate Explanation Estimation with Distribution Compression
342. ICLR 2025Efficient Dictionary Learning with Switch Sparse Autoencoders
343. ICLR 2025Efficient Top-m Data Values Identification for Data Selection
344. ICLR 2025Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
345. ICLR 2025Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies
346. ICLR 2025Enhancing Pre-trained Representation Classifiability can Boost its Interpretability
347. ICLR 2025Enhancing Prediction Performance through Influence Measure
348. ICLR 2025Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer
349. ICLR 2025Estimation of single-cell and tissue perturbation effect in spatial transcriptomics via Spatial Causal Disentanglement
350. ICLR 2025Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?

常见问题

2023–2026 年四大会议一共有多少篇社会层面 · accountability transparency and interpretability论文？

共 3,411 篇，按年份分别是 2023 年 301 篇、2024 年 589 篇、2025 年 1,164 篇、2026 年 1,357 篇。

NeurIPS 2026 有多少篇社会层面 · accountability transparency and interpretability论文？

NeurIPS 2026 有 416 篇社会层面 · accountability transparency and interpretability论文，上一届是 522 篇。

ICLR 2026 有多少篇社会层面 · accountability transparency and interpretability论文？

ICLR 2026 有 292 篇社会层面 · accountability transparency and interpretability论文，上一届是 211 篇。

ICML 2026 有多少篇社会层面 · accountability transparency and interpretability论文？

ICML 2026 有 541 篇社会层面 · accountability transparency and interpretability论文，上一届是 337 篇。

CVPR 2026 有多少篇社会层面 · accountability transparency and interpretability论文？

CVPR 2026 有 108 篇社会层面 · accountability transparency and interpretability论文，上一届是 94 篇。

哪个会议的社会层面 · accountability transparency and interpretability论文最多？

NeurIPS，2023–2026 年共 1,275 篇。