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 3,411 篇，第 16 / 69 页

751. ICML 2026PEARL: Differentially Private and Entropy-Aware Regulated Language Generation
752. ICML 2026Peer-Preservation in Frontier Models
753. ICML 2026PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
754. ICML 2026PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization
755. ICML 2026PINNfluence: Interpreting PINNs through Influence Functions
756. ICML 2026PlugGuard: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
757. ICML 2026Pluralistic Leaderboards
758. ICML 2026Poison with Style: A Practical Poisoning Attack on Code Large Language Models
759. ICML 2026Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable
760. ICML 2026PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
761. ICML 2026Post-Training with Policy Gradients: Optimality and the Base Model Barrier
762. ICML 2026PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
763. ICML 2026Predicting the Emergence of Induction Heads in Language Model Pretraining
764. ICML 2026Priority-Aware Shapley Value
765. ICML 2026Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
766. ICML 2026Privacy-Aware Data Integration for Enhanced Quantile Inference under Heterogeneity
767. ICML 2026Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
768. ICML 2026Private Learning with Public Feature Conditioning
769. ICML 2026PrivGate: Steering Contextual Integrity in LLMs via Latent Space Geometry
770. ICML 2026Proactive Defense Benchmark against Deepfake Generation
771. ICML 2026Probing Cross-modal Information Hubs in Audio-Visual LLMs
772. ICML 2026Probing RLVR Training Instability through the Lens of Objective-Level Hacking
773. ICML 2026Prompt Injection as Role Confusion
774. ICML 2026Prototype-Grounded Concept Models for Verifiable Concept Alignment
775. ICML 2026Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis
776. ICML 2026Quantifying and Optimizing Simplicity via Polynomial Representations
777. ICML 2026Quantifying Biases in LLM-as-a-Judge Evaluations
778. ICML 2026Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
779. ICML 2026Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
780. ICML 2026Query Circuits: Explaining How Language Models Answer User Prompts
781. ICML 2026Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
782. ICML 2026Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better
783. ICML 2026RAIGen: Rare Attribute Identification in Text-to-Image Generative Models
784. ICML 2026Rationality Measurement and Theory for Reinforcement Learning Agents
785. ICML 2026Reading Between the Tokens: Improving Preference Predictions through Mechanistic Forecasting
786. ICML 2026Real Data Lies: Unveiling and Closing the Quality Shortcut in Generalizable AI-Generated Video Detection
787. ICML 2026Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
788. ICML 2026Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
789. ICML 2026RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
790. ICML 2026RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
791. ICML 2026Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification
792. ICML 2026RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress
793. ICML 2026Representational Curvature Modulates Behavioral Uncertainty in Large Language Models
794. ICML 2026Resilient Coresets and Clustering
795. ICML 2026Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
796. ICML 2026Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspective
797. ICML 2026Revealing Long-context Potential of Attention Heads via Frequency Kernels
798. ICML 2026Reverse-Engineering Model Editing on Language Models
799. ICML 2026Revisiting Asymmetries in Black-box Link Stealing against Graph Neural Networks
800. ICML 2026Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

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。