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 14 / 69 页

651. ICML 2026How Language Models Process Negation
652. ICML 2026How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs
653. ICML 2026Hugging Carbon: Quantifying the Training Carbon Emissions of AI Models at Scale
654. ICML 2026HumanLM: Simulating Users with State Alignment Beats Response Imitation
655. ICML 2026HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
656. ICML 2026IACW: Intent-Aware Controllable Watermarking for Scalable Authorial Intent Attribution
657. ICML 2026Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction
658. ICML 2026Improved Algorithms for Nash Welfare in Linear Bandits
659. ICML 2026Improved Bounds for Private and Robust Alignment
660. ICML 2026Improving Adversarial Robustness of Attribution via Implicit Regularization
661. ICML 2026In-Context Universal Approximation, Compositional Generalization, and Algorithm Emulation
662. ICML 2026In-Training Defenses Against Emergent Misalignment in Language Models
663. ICML 2026Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning
664. ICML 2026Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models
665. ICML 2026Instance-Specific Approximation Ratios for Correlation Clustering and Max-Cut
666. ICML 2026Interpretability and Generalization Bounds for Learning Spatial Physics
667. ICML 2026Interpretability Driven Evolutionary Approach for the Design of Biological Sequences
668. ICML 2026Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
669. ICML 2026Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
670. ICML 2026Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow
671. ICML 2026Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks
672. ICML 2026Interpreting Genomic Language Models using Sparse Autoencoders
673. ICML 2026Introspection Adapters: Training LLMs to Report Their Learned Behaviors
674. ICML 2026IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
675. ICML 2026Is Data Shapley Not Better than Random in Data Selection? Ask NASH
676. ICML 2026Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives
677. ICML 2026IVQ: Structured and Lightweight Vector Quantization via Binary Hierarchical Composition Inspired by $\textit{IChing}$
678. ICML 2026Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
679. ICML 2026Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
680. ICML 2026Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement
681. ICML 2026Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks
682. ICML 2026Language Model Circuits Are Sparse in the Neuron Basis
683. ICML 2026LAPRAS : Learning-Augmented PRivate Answering for linear query Streams.
684. ICML 2026Large Language Models Develop Novel Social Biases Through Adaptive Exploration
685. ICML 2026LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
686. ICML 2026Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
687. ICML 2026Learning a Generative Meta-Model of LLM Activations
688. ICML 2026Learning Coherent Representations: A Topological Approach to Interpretability
689. ICML 2026Learning Efficient Guardrails for Compliance
690. ICML 2026Learning Junta Distributions, Quantum Junta States, and QAC$^0$ Circuits
691. ICML 2026Learning Manifold Data with Flow Matching
692. ICML 2026Learning to Remember, Learn, and Forget in Attention-Based Models
693. ICML 2026Learning to Watermark in the Latent Space of Generative Models
694. ICML 2026Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
695. ICML 2026LLM Self-Recognition: Steering and Retrieving Activation Signatures
696. ICML 2026LMCleaner: Efficient and Certified Online Unlearning via Influence Propagation Truncation
697. ICML 2026Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection Attack
698. ICML 2026Locate then Correct: Debiasing Attention Heads in CLIP
699. ICML 2026Long-term Fairness with Selective Labels
700. ICML 2026Low-Compute Watermark Removal via Dual-Domain Natural Projection

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。