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 40 / 69 页

1951. ICML 2025Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
1952. ICML 2025Tensor Product Neural Networks for Functional ANOVA Model
1953. ICML 2025Textual Unlearning Gives a False Sense of Unlearning
1954. ICML 2025Textural or Textual: How Vision-Language Models Read Text in Images
1955. ICML 2025The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
1956. ICML 2025The Disparate Benefits of Deep Ensembles
1957. ICML 2025The Elicitation Game: Evaluating Capability Elicitation Techniques
1958. ICML 2025The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
1959. ICML 2025The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
1960. ICML 2025The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
1961. ICML 2025The Lock-in Hypothesis: Stagnation by Algorithm
1962. ICML 2025The Power of Random Features and the Limits of Distribution-Free Gradient Descent
1963. ICML 2025The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
1964. ICML 2025The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
1965. ICML 2025The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
1966. ICML 2025The Value of Prediction in Identifying the Worst-Off
1967. ICML 2025TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
1968. ICML 2025Topological Signatures of Adversaries in Multimodal Alignments
1969. ICML 2025Towards Attributions of Input Variables in a Coalition
1970. ICML 2025Towards Black-Box Membership Inference Attack for Diffusion Models
1971. ICML 2025Towards flexible perception with visual memory
1972. ICML 2025Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models
1973. ICML 2025Towards Memorization Estimation: Fast, Formal and Free
1974. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
1975. ICML 2025Towards Trustworthy Federated Learning with Untrusted Participants
1976. ICML 2025Tracking The Best Expert Privately
1977. ICML 2025Trustworthy Machine Learning through Data-Specific Indistinguishability
1978. ICML 2025Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations
1979. ICML 2025Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
1980. ICML 2025Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
1981. ICML 2025Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
1982. ICML 2025Understanding Fixed Predictions via Confined Regions
1983. ICML 2025Understanding Model Ensemble in Transferable Adversarial Attack
1984. ICML 2025Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism
1985. ICML 2025Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
1986. ICML 2025Validating Mechanistic Interpretations: An Axiomatic Approach
1987. ICML 2025Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models
1988. ICML 2025Vision-Language Models Create Cross-Modal Task Representations
1989. ICML 2025Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
1990. ICML 2025Weak-to-Strong Jailbreaking on Large Language Models
1991. ICML 2025Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
1992. ICML 2025What makes an Ensemble (Un) Interpretable?
1993. ICML 2025When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
1994. ICML 2025Which Attention Heads Matter for In-Context Learning?
1995. ICML 2025WILTing Trees: Interpreting the Distance Between MPNN Embeddings
1996. ICML 2025WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models
1997. ICML 2025X-Hacking: The Threat of Misguided AutoML
1998. ICML 2025XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
1999. ICML 2025You Get What You Give: Reciprocally Fair Federated Learning
2000. NeurIPS 2025$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection

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。