Interpretability

Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone CVPR 2025 Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models ACL 2025 TimeInf: Time Series Data Contribution via Influence Functions ICLR 2025 TimelyMed: AI-Driven Clinical Course Attribution and Temporal Mapping for Psychiatric Medical Records IJCAI 2025 Time-series attribution maps with regularized contrastive learning AISTATS 2025 TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation ICML 2025 TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research EMNLP 2025 TLDR: Token-Level Detective Reward Model for Large Vision Language Models ICLR 2025 To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers ICML 2025 To Generate or Discriminate? Methodological Considerations for Measuring Cultural Alignment in LLMs IJCNLP 2025 Token Activation Map to Visually Explain Multimodal LLMs ICCV 2025 Token-Aware Editing of Internal Activations for Large Language Model Alignment EMNLP 2025 Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models AAAI 2025 Token Knowledge: A New Perspective For Knowledge in Large Language Models EMNLP 2025 Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models NAACL 2025 TokenShapley: Token Level Context Attribution with Shapley Value ACL 2025 TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability EMNLP 2025 Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction ICLR 2025 ToMATO: Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind AAAI 2025 Tone in Perspective: A Computational Typological Analysis of Tone Function in ASR ACL 2025 Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs EMNLP 2025 TopicAttack: An Indirect Prompt Injection Attack via Topic Transition EMNLP 2025 TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration ICML 2025 TopoLM: brain-like spatio-functional organization in a topographic language model ICLR 2025 To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts ICLR 2025