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 1,124 篇，第 6 / 23 页

251. ICML 2026How Language Models Process Negation
252. ICML 2026How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs
253. ICML 2026Hugging Carbon: Quantifying the Training Carbon Emissions of AI Models at Scale
254. ICML 2026HumanLM: Simulating Users with State Alignment Beats Response Imitation
255. ICML 2026HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
256. ICML 2026IACW: Intent-Aware Controllable Watermarking for Scalable Authorial Intent Attribution
257. ICML 2026Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction
258. ICML 2026Improved Algorithms for Nash Welfare in Linear Bandits
259. ICML 2026Improved Bounds for Private and Robust Alignment
260. ICML 2026Improving Adversarial Robustness of Attribution via Implicit Regularization
261. ICML 2026In-Context Universal Approximation, Compositional Generalization, and Algorithm Emulation
262. ICML 2026In-Training Defenses Against Emergent Misalignment in Language Models
263. ICML 2026Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning
264. ICML 2026Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models
265. ICML 2026Instance-Specific Approximation Ratios for Correlation Clustering and Max-Cut
266. ICML 2026Interpretability and Generalization Bounds for Learning Spatial Physics
267. ICML 2026Interpretability Driven Evolutionary Approach for the Design of Biological Sequences
268. ICML 2026Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
269. ICML 2026Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
270. ICML 2026Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow
271. ICML 2026Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks
272. ICML 2026Interpreting Genomic Language Models using Sparse Autoencoders
273. ICML 2026Introspection Adapters: Training LLMs to Report Their Learned Behaviors
274. ICML 2026IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
275. ICML 2026Is Data Shapley Not Better than Random in Data Selection? Ask NASH
276. ICML 2026Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives
277. ICML 2026IVQ: Structured and Lightweight Vector Quantization via Binary Hierarchical Composition Inspired by $\textit{IChing}$
278. ICML 2026Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
279. ICML 2026Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
280. ICML 2026Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement
281. ICML 2026Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks
282. ICML 2026Language Model Circuits Are Sparse in the Neuron Basis
283. ICML 2026LAPRAS : Learning-Augmented PRivate Answering for linear query Streams.
284. ICML 2026Large Language Models Develop Novel Social Biases Through Adaptive Exploration
285. ICML 2026LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
286. ICML 2026Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
287. ICML 2026Learning a Generative Meta-Model of LLM Activations
288. ICML 2026Learning Coherent Representations: A Topological Approach to Interpretability
289. ICML 2026Learning Efficient Guardrails for Compliance
290. ICML 2026Learning Junta Distributions, Quantum Junta States, and QAC$^0$ Circuits
291. ICML 2026Learning Manifold Data with Flow Matching
292. ICML 2026Learning to Remember, Learn, and Forget in Attention-Based Models
293. ICML 2026Learning to Watermark in the Latent Space of Generative Models
294. ICML 2026Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
295. ICML 2026LLM Self-Recognition: Steering and Retrieving Activation Signatures
296. ICML 2026LMCleaner: Efficient and Certified Online Unlearning via Influence Propagation Truncation
297. ICML 2026Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection Attack
298. ICML 2026Locate then Correct: Debiasing Attention Heads in CLIP
299. ICML 2026Long-term Fairness with Selective Labels
300. 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。