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 1,275 篇，第 10 / 26 页

451. NeurIPS 2025Analogy-based Multi-Turn Jailbreak against Large Language Models
452. NeurIPS 2025Angular Steering: Behavior Control via Rotation in Activation Space
453. NeurIPS 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
454. NeurIPS 2025Assignments for Congestion-Averse Agents: Seeking Competitive and Envy-Free Solutions
455. NeurIPS 2025Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
456. NeurIPS 2025Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
457. NeurIPS 2025Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool
458. NeurIPS 2025Attention Mechanism, Max-Affine Partition, and Universal Approximation
459. NeurIPS 2025Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
460. NeurIPS 2025Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives
461. NeurIPS 2025Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
462. NeurIPS 2025Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection
463. NeurIPS 2025Backdoor Cleaning without External Guidance in MLLM Fine-tuning
464. NeurIPS 2025Bandit and Delayed Feedback in Online Structured Prediction
465. NeurIPS 2025Better Language Model Inversion by Compactly Representing Next-Token Distributions
466. NeurIPS 2025Better Training Data Attribution via Better Inverse Hessian-Vector Products
467. NeurIPS 2025Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
468. NeurIPS 2025Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models
469. NeurIPS 2025Beyond Least Squares: Uniform Approximation and the Hidden Cost of Misspecification
470. NeurIPS 2025Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
471. NeurIPS 2025Beyond Prediction: Managing the Repercussions of Machine Learning Applications
472. NeurIPS 2025Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models
473. NeurIPS 2025Bilevel Network Learning via Hierarchically Structured Sparsity
474. NeurIPS 2025BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics
475. NeurIPS 2025Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs
476. NeurIPS 2025Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
477. NeurIPS 2025Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers
478. NeurIPS 2025BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
479. NeurIPS 2025Bridging Brains and Concepts: Interpretable Visual Decoding from fMRI with Semantic Bottlenecks
480. NeurIPS 2025Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts
481. NeurIPS 2025Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
482. NeurIPS 2025C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails
483. NeurIPS 2025CALM: Culturally Self-Aware Language Models
484. NeurIPS 2025Can We Infer Confidential Properties of Training Data from LLMs?
485. NeurIPS 2025CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness
486. NeurIPS 2025Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
487. NeurIPS 2025Causal Climate Emulation with Bayesian Filtering
488. NeurIPS 2025Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
489. NeurIPS 2025Causally Reliable Concept Bottleneck Models
490. NeurIPS 2025Certifying Concavity and Monotonicity in Games via Sum-of-Squares Hierarchies
491. NeurIPS 2025Channel Matters: Estimating Channel Influence for Multivariate Time Series
492. NeurIPS 2025CHASM: Unveiling Covert Advertisements on Chinese Social Media
493. NeurIPS 2025CHiQPM: Calibrated Hierarchical Interpretable Image Classification
494. NeurIPS 2025Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
495. NeurIPS 2025Collaborative Reasoner: Self-Improving Social Agents with Synthetic Conversations
496. NeurIPS 2025Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamics
497. NeurIPS 2025Concept Incongruence: An Exploration of Time and Death in Role Playing
498. NeurIPS 2025Concept-Guided Interpretability via Neural Chunking
499. NeurIPS 2025Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
500. NeurIPS 2025Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization

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。