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 1,357 篇，第 11 / 28 页

501. ICML 2026Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective
502. ICML 2026Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-Sided and Two-Sided Preconditioning
503. ICML 2026CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
504. ICML 2026CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection
505. ICML 2026Corrigibility Transformation: Constructing Goals That Accept Updates
506. ICML 2026Coupled Training with Privileged Information and Unlabeled Data
507. ICML 2026Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
508. ICML 2026DataGuard: A Non-intrusive Dataset Auditing Framework via Differential Information Forensics
509. ICML 2026DAVE: Distribution-Aware Attribution via ViT Gradient Decomposition
510. ICML 2026DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
511. ICML 2026DDIM Inversion as a Perturbation Amplifier: Breaking Mimicry Protection via Reconstruction Error Minimization
512. ICML 2026DecepChain: Inducing Deceptive Reasoning in Large Language Models
513. ICML 2026DecFus: Decentralized Layer-wise Fusion with Dynamic Exploration and Exploitation
514. ICML 2026Decomposing Query-Key Feature Interactions Using Contrastive Covariances
515. ICML 2026Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling
516. ICML 2026Decoupling Regularization and Privacy in Differentially Private Ridge Regression and ERM
517. ICML 2026Deep neural networks divide and conquer dihedral multiplication
518. ICML 2026Deep Single-Index Fréchet Regression
519. ICML 2026Delving into Muon and Beyond: Deep Analysis and Extensions
520. ICML 2026Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success
521. ICML 2026Demystifying the Optimal Fair Classifier in Multi-Class Classification
522. ICML 2026Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation
523. ICML 2026Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes
524. ICML 2026dgMARK: Decoding-Guided Watermarking for Diffusion Language Models
525. ICML 2026DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
526. ICML 2026Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
527. ICML 2026Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory
528. ICML 2026Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
529. ICML 2026Differentially Private Continual Release with Relative Error
530. ICML 2026Differentially Private Cross-Silo Recommendation from Implicit Feedback
531. ICML 2026Differentially Private Geodesic Regression
532. ICML 2026Differentially Private Range Subgraph Counting
533. ICML 2026Differentially Private Submodular Maximization with a Knapsack Constraint
534. ICML 2026Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
535. ICML 2026Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
536. ICML 2026Directly Optimizing Natural Language Explanations for Behavioral Faithfulness: Simulatability and Recoverability
537. ICML 2026Discovering Differences in Strategic Behavior between Humans and LLMs
538. ICML 2026Discovering Implicit Large Language Model Alignment Objectives
539. ICML 2026Discovering Interpretable Algorithms by Decompiling Transformers to RASP
540. ICML 2026Disentangling Geometry, Performance, and Training in Language Models
541. ICML 2026Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
542. ICML 2026Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection
543. ICML 2026Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner
544. ICML 2026Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
545. ICML 2026Distributionally Robust Reinforcement Learning from Human Feedback
546. ICML 2026Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
547. ICML 2026DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
548. ICML 2026Do Activation Verbalization Methods Convey Privileged Information?
549. ICML 2026Do Language Models Track Entities Across State Changes?
550. ICML 2026Do LLMs “Feel”? Emotion Circuits Discovery and Control

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。